Organ identification on shrimp histological images: A comparative study considering CNN and feature engineering

Abstract

The identification of shrimp organs in biology using histological images is a complex task. Shrimp histological images pose a big challenge due to their texture and similarity between classes of organs. Feature engineering and convolutional neural networks (CNN), as used for image classification, are suitable methods to assist biologists when performing organ detection. This work evaluates the Bag-of-Visual-Words (BOVW) and Pyramid-Bag-of-Words (PBOW) models for image classification using big data techniques and transfer learning for the same classification task by using a pre-trained CNN. A comparative analysis of these two different techniques is performed, highlighting the characteristics of both approaches on the problem of identification of shrimp organs.