Lightweight Small-Tailed Han Sheep Facial Recognition Based on Improved SSD Algorithm
Open Access
- 13 March 2024
- journal article
- research article
- Published by MDPI AG in Agriculture
- Vol. 14 (3) , 468
Abstract
We propose a lightweight detection algorithm based on the Single Shot MultiBox Detector (SSD) algorithm in order to facilitate sheep management and to realize sheep facial identification, and we take the self-constructed dataset as the research object. First, the SSD replaces the VGG16 backbone network with MobileNetv3, a lightweight neural network, to create a hybrid model that is much smaller. Second, the ECA attention mechanism is incorporated into the backend of the 72 × 160 bottleneck layer. Finally, the SmoothL1 loss function is substituted with the BalancedL1 loss function. The optimized model’s size decreases significantly from the original SSD’s 132 MB to just 22.4 MB. It achieves a mean average precision of 83.47% and maintains an average frame rate of 68.53 frames per second. Compared to the basic SSD model, the mean average precision has increased by 3.25 percentage points, the model size has decreased by 109.6 MB, and the detection speed has improved by 9.55 frames per second. In comparative experiments using the same dataset with different object detection models, the proposed model outperforms the SSD, Faster R-CNN, Retinanet, and CenterNet in terms of mean average precision, with improvements of 3.25 percentage points, 4.71 percentage points, 2.38 percentage points, and 8.13 percentage points, respectively. The detection speed has shown significant improvements, increasing by 9.55, 58.55, 53.1, and 12.37 frames per second, respectively. The improved model presented in this paper significantly reduces the model’s size and computational requirements while maintaining an excellent performance. This provides a valuable reference for the digitalization of animal husbandry and livestock farming.Keywords
Funding Information
- Basic Research Operating Expenses of Colleges and Universities (BR221032)
This publication has 22 references indexed in Scilit:
- Pig face recognition based on improved YOLOv4 lightweight neural networkInformation Processing in Agriculture, 2024
- Sheep face image dataset and DT-YOLOv5s for sheep breed recognitionComputers and Electronics in Agriculture, 2023
- A high-precision facial recognition method for small-tailed Han sheep based on an optimised Vision TransformerAnimal, 2023
- Research on sheep face recognition algorithm based on improved AlexNet modelNeural Computing and Applications, 2023
- Biometric facial identification using attention module optimized YOLOv4 for sheepComputers and Electronics in Agriculture, 2022
- A-MobileNet: An approach of facial expression recognitionAlexandria Engineering Journal, 2022
- Hyperspectral imaging technology combined with deep learning for hybrid okra seed identificationBiosystems Engineering, 2021
- Effects of grazing exclusion on soil carbon dynamics in alpine grasslands of the Tibetan PlateauGeoderma, 2019
- SSD: Single Shot MultiBox Detector2016
- Assessment of retinal recognition technology as a biometric method for sheep identificationComputers and Electronics in Agriculture, 2008