scholarly journals Cow Rump Identification Based on Lightweight Convolutional Neural Networks

Information ◽  
2021 ◽  
Vol 12 (9) ◽  
pp. 361
Author(s):  
Handan Hou ◽  
Wei Shi ◽  
Jinyan Guo ◽  
Zhe Zhang ◽  
Weizheng Shen ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Dairy Cow ◽  
Individual Recognition ◽  
Animal Husbandry ◽  
Identification Accuracy ◽  
Individual Identification ◽  
Production Environment ◽  
Accurate Identification ◽  
Computing Device

Individual identification of dairy cows based on computer vision technology shows strong performance and practicality. Accurate identification of each dairy cow is the prerequisite of artificial intelligence technology applied in smart animal husbandry. While the rump of each dairy cow also has lots of important features, so do the back and head, which are also important for individual recognition. In this paper, we propose a non-contact cow rump identification method based on convolutional neural networks. First, the rump image sequences of the cows while feeding were collected. Then, an object detection model was applied to detect the cow rump object in each frame of image. Finally, a fine-tuned convolutional neural network model was trained to identify cow rumps. An image dataset containing 195 different cows was created to validate the proposed method. The method achieved an identification accuracy of 99.76%, which showed a better performance compared to other related methods and a good potential in the actual production environment of cow husbandry, and the model is light enough to be deployed in an edge-computing device.

Pretrained Convolutional Neural Networks Perform Well in a Challenging Test Case: Identification of Plant Bugs (Hemiptera: Miridae) Using a Small Number of Training Images

2021 ◽  
Vol 5 (2) ◽  
Author(s):  
Alexander Knyshov ◽  
Samantha Hoang ◽  
Christiane Weirauch
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Training Image ◽  
Species Level ◽  
Identification Accuracy ◽  
Support Vector ◽  
Test Case ◽  
Learning Approaches ◽  
Lower Accuracy ◽  
Neural Network Classifiers

Abstract Automated insect identification systems have been explored for more than two decades but have only recently started to take advantage of powerful and versatile convolutional neural networks (CNNs). While typical CNN applications still require large training image datasets with hundreds of images per taxon, pretrained CNNs recently have been shown to be highly accurate, while being trained on much smaller datasets. We here evaluate the performance of CNN-based machine learning approaches in identifying three curated species-level dorsal habitus datasets for Miridae, the plant bugs. Miridae are of economic importance, but species-level identifications are challenging and typically rely on information other than dorsal habitus (e.g., host plants, locality, genitalic structures). Each dataset contained 2–6 species and 126–246 images in total, with a mean of only 32 images per species for the most difficult dataset. We find that closely related species of plant bugs can be identified with 80–90% accuracy based on their dorsal habitus alone. The pretrained CNN performed 10–20% better than a taxon expert who had access to the same dorsal habitus images. We find that feature extraction protocols (selection and combination of blocks of CNN layers) impact identification accuracy much more than the classifying mechanism (support vector machine and deep neural network classifiers). While our network has much lower accuracy on photographs of live insects (62%), overall results confirm that a pretrained CNN can be straightforwardly adapted to collection-based images for a new taxonomic group and successfully extract relevant features to classify insect species.

Dairy Cow Tiny Face Recognition Based on Convolutional Neural Networks

2019 ◽  
pp. 216-222
Author(s):  
Zehao Yang ◽  
Hao Xiong ◽  
Xiaolang Chen ◽  
Hanxing Liu ◽  
Yingjie Kuang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Face Recognition ◽  
Convolutional Neural Networks ◽  
Dairy Cow

scholarly journals Enhanced Intelligent Identification of Concrete Cracks Using Multi-Layered Image Preprocessing-Aided Convolutional Neural Networks

Sensors ◽  
2020 ◽  
Vol 20 (7) ◽  
pp. 2021 ◽  
Author(s):  
Ronghua Fu ◽  
Hao Xu ◽  
Zijian Wang ◽  
Lei Shen ◽  
Maosen Cao ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Concrete Surface ◽  
Identification Accuracy ◽  
Fine Tuning ◽  
Crack Identification ◽  
Image Preprocessing ◽  
Promising Tool ◽  
Concrete Crack ◽  
Surface Images

Crack identification plays an essential role in the health diagnosis of various concrete structures. Among different intelligent algorithms, the convolutional neural networks (CNNs) has been demonstrated as a promising tool capable of efficiently identifying the existence and evolution of concrete cracks by adaptively recognizing crack features from a large amount of concrete surface images. However, the accuracy as well as the versatility of conventional CNNs in crack identification is largely limited, due to the influence of noise contained in the background of the concrete surface images. The noise originates from highly diverse sources, such as light spots, blurs, surface roughness/wear/stains. With the aim of enhancing the accuracy, noise immunity, and versatility of CNN-based crack identification methods, a framework of enhanced intelligent identification of concrete cracks is established in this study, based on a hybrid utilization of conventional CNNs with a multi-layered image preprocessing strategy (MLP), of which the key components are homomorphic filtering and the Otsu thresholding method. Relying on the comparison and fine-tuning of classic CNN structures, networks for detection of crack position and identification of crack type are built, trained, and tested, based on a dataset composed of a large number of concrete crack images. The effectiveness and efficiency of the proposed framework involving the MLP and the CNN in crack identification are examined by comparative studies, with and without the implementation of the MLP strategy. Crack identification accuracy subject to different sources and levels of noise influence is investigated.

scholarly journals I3S Classic and Insect Species Identification of Diptera and Hymenoptera (Mosquitoes and Bees)

2016 ◽  
Author(s):  
Nayna Vyas-Patel ◽  
John D Mumford
Keyword(s):  
Apis Mellifera ◽  
Image Recognition ◽  
Bombus Terrestris ◽  
Individual Recognition ◽  
Sensu Stricto ◽  
Individual Identification ◽  
Insect Species ◽  
Identification System ◽  
Accurate Identification ◽  
The Individual

AbstractA number of image recognition systems have been specifically formulated for the individual recognition of large animals. These programs are versatile and can easily be adapted for the identification of smaller individuals such as insects. The Interactive Individual Identification System, I3S Classic, initially produced for the identification of individual whale sharks was employed to distinguish between different species of mosquitoes and bees, utilising the distinctive vein pattern present on insect wings. I3S Classic proved to be highly effective and accurate in identifying different species and sexes of mosquitoes and bees, with 80% to100% accuracy for the majority of the species tested. The sibling species Apis mellifera and Apis mellifera carnica were both identified with100% accuracy. Bombus terrestris terrestris and Bombus terrestris audax; were also identified and separated with high degrees of accuracy (90% to 100% respectively for the fore wings and 100% for the hind wings). When both Anopheles gambiae sensu stricto and Anopheles arabiensis were present in the database, they were identified with 94% and 100% accuracy respectively, allowing for a morphological and non-molecular method of sorting between these members of the sibling complex. Flat, not folded and entire, rather than broken, wing specimens were required for accurate identification. Only one wing image of each sex was required in the database to retrieve high levels of accurate results in the majority of species tested. The study describes how I3S was used to identify different insect species and draws comparisons with the use of the CO1 algorithm. As with CO1, I3S Classic proved to be suitable software which could reliably be used to aid the accurate identification of insect species. It is emphasised that image recognition for insect species should always be used in conjunction with other identifying characters in addition to the wings, as is the norm when identifying species using traditional taxonomic keys.

Rapid and accurate identification of marine microbes with single-cell Raman spectroscopy

The Analyst ◽  
2020 ◽  
Vol 145 (9) ◽  
pp. 3297-3305 ◽  
Author(s):  
Yaoyao Liu ◽  
Jingjing Xu ◽  
Yi Tao ◽  
Teng Fang ◽  
Wenbin Du ◽  
...  
Keyword(s):  
Neural Networks ◽  
Raman Spectroscopy ◽  
Single Cell ◽  
Raman Spectra ◽  
Convolutional Neural Networks ◽  
Marine Microbes ◽  
Accurate Identification ◽  
One Dimensional

Rapid and accurate identification of individual microorganisms using single-cell Raman spectra combining with one-dimensional convolutional neural networks.

scholarly journals Reinforcement learning methods based on GPU accelerated industrial control hardware

2021 ◽  
Author(s):  
Alexander Schmidt ◽  
Florian Schellroth ◽  
Marc Fischer ◽  
Lukas Allimant ◽  
Oliver Riedel
Keyword(s):  
Neural Networks ◽  
Reinforcement Learning ◽  
Real Time ◽  
Convolutional Neural Networks ◽  
Hardware Acceleration ◽  
Manufacturing Processes ◽  
Production Environment ◽  
Industrial Control ◽  
Learning Methods ◽  
The Real

AbstractReinforcement learning is a promising approach for manufacturing processes. Process knowledge can be gained automatically, and autonomous tuning of control is possible. However, the use of reinforcement learning in a production environment imposes specific requirements that must be met for a successful application. This article defines those requirements and evaluates three reinforcement learning methods to explore their applicability. The results show that convolutional neural networks are computationally heavy and violate the real-time execution requirements. A new architecture is presented and validated that allows using GPU-based hardware acceleration while meeting the real-time execution requirements.

Sign in / Sign up

Export Citation Format

Share Document