Western Mediterranean Wetland Birds dataset: A new annotated dataset for acoustic bird species classification

The deployment of an expert system running over a wireless acoustic sensors network made up of bioacoustic monitoring devices that recognize bird species from their sounds would enable the automation of many tasks of ecological value, including the analysis of bird population composition or the detection of endangered species in areas of environmental interest. Endowing these devices with accurate audio classification capabilities is possible thanks to the latest advances in artificial intelligence, among which deep learning techniques stand out. To train such algorithms, data from the sources to be classified is required. For this reason, this paper presents the Western Mediterranean Wetland Birds (WMWB) dataset, consisting of 201.6 min and 5795 annotated audio excerpts of 20 endemic bird species of the Aiguamolls de l'Empordà Natural Park. The main objective of this work is to describe and analyze this new dataset. Moreover, this work presents the results of bird species classification experiments using four well- known deep neural networks fine-tuned on our dataset, whose models are also made public along with the dataset. These results are aimed to serve as a performance baseline reference for the community when using the WMWB dataset for their experiments.     

Wildlife surveillance using deep learning methods

相似文献   

Cross-domain retinopathy classification with optical coherence tomography images via a novel deep domain adaptation method

Deep learning based retinopathy classification with optical coherence tomography (OCT) images has recently attracted great attention. However, existing deep learning methods fail to work well when training and testing datasets are different due to the general issue of domain shift between datasets caused by different collection devices, subjects, imaging parameters, etc. To address this practical and challenging issue, we propose a novel deep domain adaptation (DDA) method to train a model on a labeled dataset and adapt it to an unlabelled dataset (collected under different conditions). It consists of two modules for domain alignment, that is, adversarial learning and entropy minimization. We conduct extensive experiments on three public datasets to evaluate the performance of the proposed method. The results indicate that there are large domain shifts between datasets, resulting a poor performance for conventional deep learning methods. The proposed DDA method can significantly outperform existing methods for retinopathy classification with OCT images. It achieves retinopathy classification accuracies of 0.915, 0.959 and 0.990 under three cross-domain (cross-dataset) scenarios. Moreover, it obtains a comparable performance with human experts on a dataset where no labeled data in this dataset have been used to train the proposed DDA method. We have also visualized the learnt features by using the t-distributed stochastic neighbor embedding (t-SNE) technique. The results demonstrate that the proposed method can learn discriminative features for retinopathy classification.     

Three critical factors affecting automated image species recognition performance for camera traps

Ecological camera traps are increasingly used by wildlife biologists to unobtrusively monitor an ecosystems animal population. However, manual inspection of the images produced is expensive, laborious, and time‐consuming. The success of deep learning systems using camera trap images has been previously explored in preliminary stages. These studies, however, are lacking in their practicality. They are primarily focused on extremely large datasets, often millions of images, and there is little to no focus on performance when tasked with species identification in new locations not seen during training. Our goal was to test the capabilities of deep learning systems trained on camera trap images using modestly sized training data, compare performance when considering unseen background locations, and quantify the gradient of lower bound performance to provide a guideline of data requirements in correspondence to performance expectations. We use a dataset provided by Parks Canada containing 47,279 images collected from 36 unique geographic locations across multiple environments. Images represent 55 animal species and human activity with high‐class imbalance. We trained, tested, and compared the capabilities of six deep learning computer vision networks using transfer learning and image augmentation: DenseNet201, Inception‐ResNet‐V3, InceptionV3, NASNetMobile, MobileNetV2, and Xception. We compare overall performance on “trained” locations where DenseNet201 performed best with 95.6% top‐1 accuracy showing promise for deep learning methods for smaller scale research efforts. Using trained locations, classifications with <500 images had low and highly variable recall of 0.750 ± 0.329, while classifications with over 1,000 images had a high and stable recall of 0.971 ± 0.0137. Models tasked with classifying species from untrained locations were less accurate, with DenseNet201 performing best with 68.7% top‐1 accuracy. Finally, we provide an open repository where ecologists can insert their image data to train and test custom species detection models for their desired ecological domain.     

LEMOXINET: Lite ensemble MobileNetV2 and Xception models to predict plant disease

Plant diseases play a significant role in agricultural production, in which early detection of plant diseases is deemed an essential task. Current computational intelligence and computer vision methods have been promising to improve disease diagnosis. Convolutional Neural Networks (CNN) models are capable of detecting plant diseases in an agricultural field and plantation leaf images. MobileNetV2 refers to an appropriate CNN model for mobile devices with subordinate parameters and model file sizes. However, the effectiveness of MobileNetV2 requires improvement to capture more critical features. Xception refers to the extension of InceptionV3 with fewer and excellent parameters in extracting features. This research suggests an ensemble of MobileNetV2 and Xception by concatenating the extracted features to improve plant disease detection performance. This study indicated that MobileNetV2, Xception, and ensemble model achieved 97.32%, 98.30%, and 99.10% accuracy when considering the entire Plant Village dataset. Particularly, MobileNetV2 and Xception models' accuracy improved by 1.8% and 0.8%, respectively. In addition, our model captures 99.52% of all metric scores in the user-defined dataset. Our model indicated better performance than the seven state-of-the-art CNN models, both individually and in ensemble design. It can be integrated with mobile devices, providing fewer parameters and model file size than an ensemble of MobileNetV2 with InceptionResnetV2, VGG19, and VGG16.     

Multi-view features fusion for birdsong classification

As important members of the ecosystem, birds are good monitors of the ecological environment. Bird recognition, especially birdsong recognition, has attracted more and more attention in the field of artificial intelligence. At present, traditional machine learning and deep learning are widely used in birdsong recognition. Deep learning can not only classify and recognize the spectrums of birdsong, but also be used as a feature extractor. Machine learning is often used to classify and recognize the extracted birdsong handcrafted feature parameters. As the data samples of the classifier, the feature of birdsong directly determines the performance of the classifier. Multi-view features from different methods of feature extraction can obtain more perfect information of birdsong. Therefore, aiming at enriching the representational capacity of single feature and getting a better way to combine features, this paper proposes a birdsong classification model based multi-view features, which combines the deep features extracted by convolutional neural network (CNN) and handcrafted features. Firstly, four kinds of handcrafted features are extracted. Those are wavelet transform (WT) spectrum, Hilbert-Huang transform (HHT) spectrum, short-time Fourier transform (STFT) spectrum and Mel-frequency cepstral coefficients (MFCC). Then CNN is used to extract the deep features from WT, HHT and STFT spectrum, and the minimal-redundancy-maximal-relevance (mRMR) to select optimal features. Finally, three classification models (random forest, support vector machine and multi-layer perceptron) are built with the deep features and handcrafted features, and the probability of classification results of the two types of features are fused as the new features to recognize birdsong. Taking sixteen species of birds as research objects, the experimental results show that the three classifiers obtain the accuracy of 95.49%, 96.25% and 96.16% respectively for the features of the proposed method, which are better than the seven single features and three fused features involved in the experiment. This proposed method effectively combines the deep features and handcrafted features from the perspectives of signal. The fused features can more comprehensively express the information of the bird audio itself, and have higher classification accuracy and lower dimension, which can effectively improve the performance of bird audio classification.     

Columnar cactus recognition in aerial images using a deep learning approach

Tehuacán-Cuicatlán Valley is a semi-arid zone in the south of Mexico. It was inscribed in the World Heritage List by the UNESCO in 2018. This unique area has wide biodiversity including several endemic plants. Unfortunately, human activity is constantly affecting the area. A way to preserve a protected area is to carry out autonomous surveillance of the area. A first step to reach this autonomy is to automatically detect and recognize elements in the area. In this work, we present a deep learning based approach for columnar cactus recognition, specifically, the Neobuxbaumia tetetzo species, endemic of the Valley. An image dataset was generated for this study by our research team, containing more than 10,000 image examples. The proposed approach uses this dataset to train a modified LeNet-5 Convolutional Neural Network. Experimental results have shown a high recognition accuracy, 0.95 for the validation set, validating the use of the approach for columnar cactus recognition.     

Performance analysis of real-time plant species recognition using bilateral network combined with machine learning classifier

A real-time plant species recognition under an unconstrained environment is a challenging and time-consuming process. The recognition model should cope up with the computer vision challenges such as scale variations, illumination changes, camera viewpoint or object orientation changes, cluttered backgrounds and structure of leaf (simple or compound). In this paper, a bilateral convolutional neural network (CNN) with machine learning classifiers are investigated in relation to the real-time implementation of plant species recognition. The CNN models considered are MobileNet, Xception and DenseNet-121. In the bilateral CNNs (Homogeneous/Heterogeneous type), the models are connected using the cascade early fusion strategy. The Bilateral CNN is used in the process of feature extraction. Then, the extracted features are classified using different machine learning classifiers such as Linear Discriminant Analysis (LDA), multinomial Logistic Regression (MLR), Naïve Bayes (NB), k-Nearest Neighbor (k−NN), Classification and Regression Tree (CART), Random Forest Classifier (RF), Bagging Classifier (BC), Multi-Layer Perceptron (MLP) and Support Vector Machine (SVM). From the experimental investigation, it is observed that the multinomial Logistic Regression classifier performed better compared to other classifiers, irrespective of the bilateral CNN models (Homogeneous - MoMoNet, XXNet, DeDeNet; Heterogeneous - MoXNet, XDeNet, MoDeNet). It is also observed that the MoDeNet + MLR model attained the state-of-the-art results (Flavia: 98.71%, Folio: 96.38%, Swedish Leaf: 99.41%, custom created Leaf-12: 99.39%), irrespective of the dataset. The number of misprediction/class is highly reduced by utilizing the MoDeNet + MLR model for real-time plant species recognition.     

Deep learning-based segmentation for disease identification

Plant diseases have recently increased and exacerbated due to several factors such as climate change, chemicals’ misuse and pollution. They represent a severe threat for both economy and global food security. Recently, several researches have been proposed for plant disease identification through modern image-based recognition systems based on deep learning. However, several challenges still require further investigation. One is related to the high variety of leaf diseases/ species along with constraints related to the collection and annotation of real-world datasets. Other challenges are related to the study of leaf disease in uncontrolled environment. Compared to major existing researches, we propose in this article a new perspective to handle the problem with two main differences: First, while most approach aims to identify simultaneously a pair of species-disease, we propose to identify diseases independently of leaf species. This helps to recognize new species holding diseases that were previously learnt. Moreover, instead of using the global leaf image, we directly predict disease on the basis of the local disease symptom features. We believe that this may decrease the bias related to common context and/or background and enables to build a more generalised model for disease classification. In particular, we propose an hybrid system that combines strengths of deep learning-based semantic segmentation with classification capabilities to respectively extract infected regions and determine their identity. For that, an extensive experimentation including a comparison of different semantic segmentation and classification CNNs has been conducted on PlantVillage dataset (leaves within homogeneous background) in order to study the extent of use of local disease symptoms features to identify diseases. Specifically, a particular enhancement of disease identification accuracy has been demonstrated in IPM and BING datasets (leaves within uncontrolled background).     

Detection and classification of chilli leaf disease using a squeeze-and-excitation-based CNN model

Chilli leaf disease has a destructive effect on the chilli crop yield. Chilli leaf disease can result in a significant decrease in both the quantity and quality of the chilli crop. Early detection, perfect identification and accurately diagnosing the disease will aid in increasing the profit of the cultivator. However, after a comprehensive survey investigation, we discovered that no studies have been previously conducted to compare the classification performance of machine learning and deep learning for the chilli leaf disease classification problem. In this study, five main leaf diseases i.e. down curl of a leaf, Geminivirus, Cercospora leaf spot, yellow leaf disease, and up curl disease were identified, and images were captured using a digital camera and are labelled. These diseases were classified using 12 different pretrained deep learning networks (AlexNet, DarkNet53, DenseNet201, EfficientNetb0, InceptionV3, MobileNetV2, NasNetLarge, ResNet101, ShuffleNet, SqueezeNet, VGG19, and XceptionNet) using chilli leaf data with and without augmentation using deep learning transfer. Performance metrics such as accuracy, recall, precision, F1-score, specificity, and misclassification were calculated for each network. VGG19 had the best accuracy (83.54%) without augmentation, and DarkNet53 had the best result (98.82%) with augmentation among all pretrained deep learning networks in our self-built chilli leaf dataset. The result was enhanced by designing a squeeze-and-excitation-based convolutional neural network (SECNN) model. The model was tested on a chilli leaf dataset with different input sizes and mini-batch sizes. The proposed model produced the best accuracy of 98.63% and 99.12% without and with augmentation, respectively. The SECNN model was also tested on different datasets from the PlantVillage data, including apple, cherry, corn, grape, peach, pepper, potato, strawberry, and tomato leaves, separately and with the chilli dataset. The proposed model achieved an accuracy of 99.28% in classifying 43 different classes of plant leaf datasets.     

An approach to multi-class imbalanced problem in ecology using machine learning

Ecologists collect their data manually by visiting multiple sampling sites. Since there can be multiple species in the multiple sampling sites, manually classifying them can be a daunting task. Much work in literature has focused mostly on statistical methods for classification of single species and very few studies on classification of multiple species. In addition to looking at multiple species, we noted that classification of multiple species result in multi-class imbalanced problem. This study proposes to use machine learning approach to classify multiple species in population ecology. In particular, bagging (random forests (RF) and bagging classification trees (bagCART)) and boosting (boosting classification trees (bootCART), gradient boosting machines (GBM) and adaptive boosting classification trees (AdaBoost)) classifiers were evaluated for their performances on imbalanced multiple fish species dataset. The recall and F1-score performance metrics were used to select the best classifier for the dataset. The bagging classifiers (RF and bagCART) achieved high performances on the imbalanced dataset while the boosting classifiers (bootCART, GBM and AdaBoost) achieved lower performances on the imbalanced dataset. We found that some machine learning classifiers were sensitive to imbalanced dataset hence they require data resampling to improve their performances. After resampling, the bagging classifiers (RF and bagCART) had high performances compared to boosting classifiers (bootCART, GBM and AdaBoost). The strong performances shown by bagging classifiers (RF and bagCART) suggest that they can be used for classifying multiple species in ecological studies.     

Towards automatic wild animal monitoring: Identification of animal species in camera-trap images using very deep convolutional neural networks

Non-intrusive monitoring of animals in the wild is possible using camera trapping networks. The cameras are triggered by sensors in order to disturb the animals as little as possible. This approach produces a high volume of data (in the order of thousands or millions of images) that demands laborious work to analyze both useless (incorrect detections, which are the most) and useful (images with presence of animals). In this work, we show that as soon as some obstacles are overcome, deep neural networks can cope with the problem of the automated species classification appropriately. As case of study, the most common 26 of 48 species from the Snapshot Serengeti (SSe) dataset were selected and the potential of the Very Deep Convolutional neural networks framework for the species identification task was analyzed. In the worst-case scenario (unbalanced training dataset containing empty images) the method reached 35.4% Top-1 and 60.4% Top-5 accuracy. For the best scenario (balanced dataset, images containing foreground animals only, and manually segmented) the accuracy reached a 88.9% Top-1 and 98.1% Top-5, respectively. To the best of our knowledge, this is the first published attempt on solving the automatic species recognition on the SSe dataset. In addition, a comparison with other approaches on a different dataset was carried out, showing that the architectures used in this work outperformed previous approaches. The limitations of the method, drawbacks, as well as new challenges in automatic camera-trap species classification are widely discussed.     

New image dataset and new negative sample judgment method for crop pest recognition based on deep learning models

Crop pests are responsible for serious economic loss around the worldwide. Accurate recognition of pests is the key to pest control and is a considerable challenge in farming. Deep learning models have shown great promise in image recognition, drawing the attention of many agricultural experts. However, the lack of pest image datasets and the inexplicability of deep learning models have hindered the development of deep learning models in the field of pest recognition. Our work provides the following four contributions: (1) We constructed a new and more effective dataset, for crop pest recognition, named IP41 comprising 46,567 original images of crop pests in 41 classes. (2) We trained three different deep learning models based on IP41, using transfer learning combined with fine-tuning. The results of the three deep learning models exceeded 80.00% recognition. (3) A negative sample judgment method was proposed to exclude the uploaded pest-free images of the user. (4) We provided reasonable visual explanations for the most critical areas of the recognition layers by using the gradient-weighted class activation mapping method. This research suggests that the recognition process focuses more on image details than the image as a whole, and that overall difference is ignored to a certain extent. These results will be helpful to future research in the field of agricultural pest recognition     

Wood Recognition Using Image Texture Features

Inspired by theories of higher local order autocorrelation (HLAC), this paper presents a simple, novel, yet very powerful approach for wood recognition. The method is suitable for wood database applications, which are of great importance in wood related industries and administrations. At the feature extraction stage, a set of features is extracted from Mask Matching Image (MMI). The MMI features preserve the mask matching information gathered from the HLAC methods. The texture information in the image can then be accurately extracted from the statistical and geometrical features. In particular, richer information and enhanced discriminative power is achieved through the length histogram, a new histogram that embodies the width and height histograms. The performance of the proposed approach is compared to the state-of-the-art HLAC approaches using the wood stereogram dataset ZAFU WS 24. By conducting extensive experiments on ZAFU WS 24, we show that our approach significantly improves the classification accuracy.     

BLeafNet: A Bonferroni mean operator based fusion of CNN models for plant identification using leaf image classification

Plants, the only natural source of oxygen, are the most important resources for every species in the world. A proper identification of plants is important for different fields. The observation of leaf characteristics is a popular method as leaves are easily available for examination. Researchers are increasingly applying image processing techniques for the identification of plants based on leaf images. In this paper, we have proposed a leaf image classification model, called BLeafNet, for plant identification, where the concept of deep learning is combined with Bonferroni fusion learning. Initially, we have designed five classification models, using ResNet-50 architecture, where five different inputs are separately used in the models. The inputs are the five variants of the leaf grayscale images, RGB, and three individual channels of RGB - red, green, and blue. For fusion of the five ResNet-50 outputs, we have used the Bonferroni mean operator as it expresses better connectivity among the confidence scores, and it also obtains better results than the individual models. We have also proposed a two-tier training method for properly training the end-to-end model. To evaluate the proposed model, we have used the Malayakew dataset, collected at the Royal Botanic Gardens in New England, which is a very challenging dataset as many leaves from different species have a very similar appearance. Besides, the proposed method is evaluated using the Leafsnap and the Flavia datasets. The obtained results on both the datasets confirm the superiority of the model as it outperforms the results achieved by many state-of-the-art models.     

A study on giant panda recognition based on images of a large proportion of captive pandas

1. As a highly endangered species, the giant panda (panda) has attracted significant attention in the past decades. Considerable efforts have been put on panda conservation and reproduction, offering the promising outcome of maintaining the population size of pandas. To evaluate the effectiveness of conservation and management strategies, recognizing individual pandas is critical. However, it remains a challenging task because the existing methods, such as traditional tracking method, discrimination method based on footprint identification, and molecular biology method, are invasive, inaccurate, expensive, or challenging to perform. The advances of imaging technologies have led to the wide applications of digital images and videos in panda conservation and management, which makes it possible for individual panda recognition in a noninvasive manner by using image‐based panda face recognition method.
2. In recent years, deep learning has achieved great success in the field of computer vision and pattern recognition. For panda face recognition, a fully automatic deep learning algorithm which consists of a sequence of deep neural networks (DNNs) used for panda face detection, segmentation, alignment, and identity prediction is developed in this study. To develop and evaluate the algorithm, the largest panda image dataset containing 6,441 images from 218 different pandas, which is 39.78% of captive pandas in the world, is established.
3. The algorithm achieved 96.27% accuracy in panda recognition and 100% accuracy in detection.
4. This study shows that panda faces can be used for panda recognition. It enables the use of the cameras installed in their habitat for monitoring their population and behavior. This noninvasive approach is much more cost‐effective than the approaches used in the previous panda surveys.

     

Research on Plant Species Identification Based on Improved Convolutional Neural Network

Plant species recognition is an important research area in image recognition in recent years. However, the existing plant species recognition methods have low recognition accuracy and do not meet professional requirements in terms of recognition accuracy. Therefore, ShuffleNetV2 was improved by combining the current hot concern mechanism, convolution kernel size adjustment, convolution tailoring, and CSP technology to improve the accuracy and reduce the amount of computation in this study. Six convolutional neural network models with sufficient trainable parameters were designed for differentiation learning. The SGD algorithm is used to optimize the training process to avoid overfitting or falling into the local optimum. In this paper, a conventional plant image dataset TJAU10 collected by cell phones in a natural context was constructed, containing 3000 images of 10 plant species on the campus of Tianjin Agricultural University. Finally, the improved model is compared with the baseline version of the model, which achieves better results in terms of improving accuracy and reducing the computational effort. The recognition accuracy tested on the TJAU10 dataset reaches up to 98.3%, and the recognition precision reaches up to 93.6%, which is 5.1% better than the original model and reduces the computational effort by about 31% compared with the original model. In addition, the experimental results were evaluated using metrics such as the confusion matrix, which can meet the requirements of professionals for the accurate identification of plant species.     

Estimating dataset size requirements for classifying DNA microarray data.

A statistical methodology for estimating dataset size requirements for classifying microarray data using learning curves is introduced. The goal is to use existing classification results to estimate dataset size requirements for future classification experiments and to evaluate the gain in accuracy and significance of classifiers built with additional data. The method is based on fitting inverse power-law models to construct empirical learning curves. It also includes a permutation test procedure to assess the statistical significance of classification performance for a given dataset size. This procedure is applied to several molecular classification problems representing a broad spectrum of levels of complexity.     

Deep Convolution Neural Network Based System for Early Diagnosis of Alzheimer's Disease

ObjectivesAlzheimer's Disease (AD) is the most general type of dementia. In all leading countries, it is one of the primary reasons of death in senior citizens. Currently, it is diagnosed by calculating the MSME score and by the manual study of MRI Scan. Also, different machine learning methods are utilized for automatic diagnosis but existing has some limitations in terms of accuracy. So, main objective of this paper to include a preprocessing method before CNN model to increase the accuracy of classification.Materials and methodIn this paper, we present a deep learning-based approach for detection of Alzheimer's Disease from ADNI database of Alzheimer's disease patients, the dataset contains fMRI and PET images of Alzheimer's patients along with normal person's image. We have applied 3D to 2D conversion and resizing of images before applying VGG-16 architecture of Convolution neural network for feature extraction. Finally, for classification SVM, Linear Discriminate, K means clustering, and Decision tree classifiers are used.ResultsThe experimental result shows that the average accuracy of 99.95% is achieved for the classification of the fMRI dataset, while the average accuracy of 73.46% is achieved with the PET dataset. On comparing results on the basis of accuracy, specificity, sensitivity and on some other parameters we found that these results are better than existing methods.Conclusionsthis paper, suggested a unique way to increase the performance of CNN models by applying some preprocessing on image dataset before sending to CNN architecture for feature extraction. We applied this method on ADNI database and on comparing the accuracies with other similar approaches it shows better results.     

Soil suitability classification for crop selection in precision agriculture using GBRT-based hybrid DNN surrogate models

The main reason for agricultural productivity decline is farmers' failure to choose the appropriate crop for their soil. It is important for farmers to understand which crops are suitable for different soil types based on their characteristics. Due to the vast variety of soil types worldwide, farmers often struggle to choose the most profitable crop for their land. To improve crop yields, a crop selection system has been developed using GBRT-based deep learning surrogate models. Gradient Boosted Regression Tree (GBRT) has been combined with a Bayesian optimization (BO) algorithm to determine the most optimal hyperparameters for the deep neural network. The optimized hyperparameters are then applied during the testing phase. Further, the impact of each input parameter on the individual outputs is evaluated using explainable artificial intelligence (XAI). The crop recommendation system comprises data preparation, classification, and performance evaluation modules. A classification method based on confusion matrices and performance matrices, as well as feature analysis using density plots and correlation plots, follows. The crop selection system categorizes the experimental dataset into 12 classes, with three for each of the four crops. The dataset includes soil-specific physical and chemical features such as sand, silt, clay, pH, electric conductivity (EC), soil organic carbon (SOC), nitrogen (N), phosphorus (P), and potassium (K). The developed surrogate model is highly accurate, precise, and reliable, with an F1-Score of 1.0 for all classes in the dataset, indicating exact accuracy and recall. The DNN-based classification model achieves an average classification accuracy of 1.00.