Authors:
Jack Hollister
1
;
Rodrigo Vega
1
and
M. A. Hannan Bin Azhar
2
Affiliations:
1
School of Psychology and Life Sciences, Canterbury Church University, U.K.
;
2
School of Engineering, Technology and Design, Canterbury Christ Church University, U.K.
Keyword(s):
Freshwater Ecology, Computer Vison, Object Detection, Image Classification, Chironomidae, Chironomid, Faster-RCNN, SSD, Raspberry Pi, TensorFlow.
Abstract:
This paper introduces an automated method for the identification of chironomid larvae mounted on microscope slides in the form of a computer-based identification tool using deep learning techniques. Using images of chironomid head capsules, a series of object detection models were created to classify three genera. These models were then used to show how pre-training preparation could improve the final performance. The model comparisons included two object detection frameworks (Faster-RCNN and SSD frameworks), three balanced image sets (with and without augmentation) and variations of two hyperparameter values (Learning Rate and Intersection Over Union). All models were reported using mean average precision or mAP. Multiple runs of each model configuration were carried out to assess statistical significance of the results. The highest mAP value achieved was 0.751 by Faster-RCNN. Statistical analysis revealed significant differences in mAP values between the two frameworks. When experi
menting with hyperparameter values, the combination of learning rates and model architectures showed significant relationships. Although all models produced similar accuracy results (94.4% - 97.8%), the confidence scores varied widely.
(More)