Automatic identification of non-biting midges (Chironomidae) using object detection and deep learning techniques
Hollister, Jack, Vega, Rodrigo and Azhar, M. A. Hannan Bin 2022. Automatic identification of non-biting midges (Chironomidae) using object detection and deep learning techniques. in: Marsico, Maria D., Sanniti de Baja, Gabriella and Fred, Ana (ed.) Proceedings of the 11 International Conference on Pattern Recognition Applications and Methods SCITEPRESS - Science and Technology Publications.
|Authors||Hollister, Jack, Vega, Rodrigo and Azhar, M. A. Hannan Bin|
|Editors||Marsico, Maria D., Sanniti de Baja, Gabriella and Fred, Ana|
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 experimenting 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.
|Keywords||Freshwater ecology; Computer vison; Object detection; Image classification; Chironomidae; Chironomid; Faster-RCNN; SSD; Raspberry Pi; TensorFlow|
|Book title||Proceedings of the 11 International Conference on Pattern Recognition Applications and Methods|
|Publisher||SCITEPRESS - Science and Technology Publications|
|Publication process dates|
|Deposited||28 Feb 2022|
|Digital Object Identifier (DOI)||https://doi.org/10.5220/0010822800003122|
Topics: Bioinformatics and Systems Biology; Deep Learning and Neural Networks; Image and Video Analysis and Understanding; Industry Related Applications
Registration required on publisher's website to view paper.
2views this month
0downloads this month