Recognition of Cattle Using Face Images

Kumar, Santosh; Singh, Sanjay Kumar; Singh, Rishav; Singh, Amit Kumar

doi:10.1007/978-981-10-7956-6_3

Cited by 11 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to the use of regular ear tags and RFID ear tags, the cattle biometrics and visual features have emerged as a promising cattle identification mechanism (Qiao et al, 2021). The new mechanism can be classified into four categories (Qiao et al, 2021): cattle muzzle (Kusakunniran et al, 2018), iris (Lu et al, 2014), facial (Kumar et al, 2017), and coat pattern (Andrew et al, 2016). However, that modern biometric-based methods still require further research before large-scale applications (Awad 2016).…”

Section: Similar Systems In Other Countriesmentioning

confidence: 99%

Modeling e-Livestock Indonesia

Ramadhan

Arymurthy

Sensuse

et al. 2021

Heliyon

View full text Add to dashboard Cite

Indonesia is always increasing every year. However, Indonesia's national beef supply cannot meet those needs. The import of beef in large numbers likely to remain performed. The government has made various efforts to reduce imports and achieve self-sufficiency in beef. However, the government does not yet have a good identification, registration, documentation, and traceability system, so there is no truly valid data regarding the actual stock condition. Inaccuracy of data can lead to inappropriate policymaking in the livestock sector. Therefore, an e-Government initiative in the form of e-Livestock has been proposed. The definitions and success factors regarding e-Livestock have been revealed in our previous researches. Based on those researches, by using soft system methodology, hermeneutics, focus group discussion, and success factors, the business process models for e-Livestock in Indonesia will be created in this research. Apart from that, various kinds of recommendations for action to solve the problem will also be generated from this research. Those recommendations are about the functional requirement, the identification tool, the location numbering rule, the ownership documentation, the socialization of the e-Livestock, the institutional aspect of e-Livestock, the regulations underlie e-Livestock and the conceptual infrastructure diagram of e-Livestock. All of the business process models produced have been validated and their complexities are also calculated. Most of the business process model is very easy to understand. All the business process models and recommendations generated from this research can be a guide for the government when implementing e-Livestock.

show abstract

Section: Similar Systems In Other Countriesmentioning

confidence: 99%

Modeling e-Livestock Indonesia

Ramadhan

Arymurthy

Sensuse

et al. 2021

Heliyon

View full text Add to dashboard Cite

show abstract

“…For example, biometric and visual features, extracted from images of cattle muzzle, face, coat, torso, retinas and irises, have been shown to be helpful for identifying cattle (Jiang et al, 2019;Guzhva et al, 2021). Cai and Li (2013) and Kumar et al (2017) presented a facial representation model of cattle based on extracted facial features, while Gaber et al (2016) used the Weber Local Descriptor to extract robust features from cattle muzzle print images for cattle identification. Similarly, Kusakunniran et al (2018) proposed an automatic cattle identification approach by fusing visual features extracted from muzzle images, while Andrew et al (2016) utilized cattle coat patterns for identification.…”

Section: Related Workmentioning

confidence: 99%

Automated Individual Cattle Identification Using Video Data: A Unified Deep Learning Architecture Approach

et al. 2021

View full text Add to dashboard Cite

Individual cattle identification is a prerequisite and foundation for precision livestock farming. Existing methods for cattle identification require radio frequency or visual ear tags, all of which are prone to loss or damage. Here, we propose and implement a new unified deep learning approach to cattle identification using video analysis. The proposed deep learning framework is composed of a Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) with a self-attention mechanism. More specifically, the Inception-V3 CNN was used to extract features from a cattle video dataset taken in a feedlot with rear-view. Extracted features were then fed to a BiLSTM layer to capture spatio-temporal information. Then, self-attention was employed to provide a different focus on the features captured by BiLSTM for the final step of cattle identification. We used a total of 363 rear-view videos from 50 cattle at three different times with an interval of 1 month between data collection periods. The proposed method achieved 93.3% identification accuracy using a 30-frame video length, which outperformed current state-of-the-art methods (Inception-V3, MLP, SimpleRNN, LSTM, and BiLSTM). Furthermore, two different attention schemes, namely, additive and multiplicative attention mechanisms were compared. Our results show that the additive attention mechanism achieved 93.3% accuracy and 91.0% recall, greater than multiplicative attention mechanism with 90.7% accuracy and 87.0% recall. Video length also impacted accuracy, with video sequence length up to 30-frames enhancing identification performance. Overall, our approach can capture key spatio-temporal features to improve cattle identification accuracy, enabling automated cattle identification for precision livestock farming.

show abstract

Computer Vision and Machine Learning in Agriculture: An Introduction

Bansal

Uddin

2023

Computer Vision and Machine Learning in Agriculture, Volume 3

View full text Add to dashboard Cite

Recognition of Cattle Using Face Images

Cited by 11 publications

References 36 publications

Modeling e-Livestock Indonesia

Modeling e-Livestock Indonesia

Automated Individual Cattle Identification Using Video Data: A Unified Deep Learning Architecture Approach

Computer Vision and Machine Learning in Agriculture: An Introduction

Contact Info

Product

Resources

About