Towards Machine Vision for Insect Welfare Monitoring and Behavioural Insights

Perspectives of FTIR as Promising Tool for Pathogen Diagnosis, Sanitary and Welfare Monitoring in Animal Experimentation Models: A Review Based on Pertinent Literature

Currently, there is a wide application in the literature of the use of the Fourier Transform Infrared Spectroscopy (FTIR) technique. This basic tool has also proven to be efficient for detecting molecules associated with hosts and pathogens in infections, as well as other molecules present in humans and animals' biological samples. However, there is a crisis in science data reproducibility. This crisis can also be observed in data from experimental animal models (EAMs). When it comes to rodents, a major challenge is to carry out sanitary monitoring, which is currently expensive and requires a large volume of biological samples, generating ethical, legal, and psychological conflicts for professionals and researchers. We carried out a survey of data from the relevant literature on the use of this technique in different diagnostic protocols and combined the data with the aim of presenting the technique as a promising tool for use in EAM. Since FTIR can detect molecules associated with different diseases and has advantages such as the low volume of samples required, low cost, sustainability, and provides diagnostic tests with high specificity and sensitivity, we believe that the technique is highly promising for the sanitary and stress and the detection of molecules of interest of infectious or non-infectious origin.

PDC: Pearl Detection with a Counter Based on Deep Learning

Pearl detection with a counter (PDC) in a noncontact and high-precision manner is a challenging task in the area of commercial production. Additionally, sea pearls are considered to be quite valuable, so the traditional manual counting methods are not satisfactory, as touching may cause damage to the pearls. In this paper, we conduct a comprehensive study on nine object-detection models, and the key metrics of these models are evaluated. The results indicate that using Faster R-CNN with ResNet152, which was pretrained on the pearl dataset, mAP@0.5IoU = 100% and mAP@0.75IoU = 98.83% are achieved for pearl recognition, requiring only 15.8 ms inference time with a counter after the first loading of the model. Finally, the superiority of the proposed algorithm of Faster R-CNN ResNet152 with a counter is verified through a comparison with eight other sophisticated object detectors with a counter. The experimental results on the self-made pearl image dataset show that the total loss decreased to 0.00044. Meanwhile, the classification loss and the localization loss of the model gradually decreased to less than 0.00019 and 0.00031, respectively. The robust performance of the proposed method across the pearl dataset indicates that Faster R-CNN ResNet152 with a counter is promising for natural light or artificial light peal detection and accurate counting.