Carp-DCAE: Deep convolutional autoencoder for carp fish classification

Arnab Banerjee, Arijit Das, Samarendra Behra, Debotosh Bhattacharjee, Nagesh Talagunda Srinivasan, Mita Nasipuri, Nibaran Das

Abstract: Highlights•The latent features of Simple (SAE), Deep (DAE), and Convolutional deep (DCAE) autoencoder models are extracted and utilised to identify the major carp species. The experiment is conducted using a standard dataset of 1500 photos (500 images of each species) of three major carp species: Labeo catla (Catla), Labeo rohita (Rohu), and Cirrhinus cirrhosus (Mrigal).•The major carp fish species are identified using two methods: one involves adding a fully connected layer at the end of the autoencoder network, and the other involves combining the autoencoder network with typical machine learning algorithms such as Logistic Regression, Naive-Bayse, K-Nearest Neighbor, Support Vector Machine, and Random Forest.•All of the experiments are carried out incrementally on the acquired data in order to assess the efficacy of our suggested approach as the amount of data increases.•The results of the proposed approach is compared with the result using some traditional image descriptors: 206 Hu moments, Haralick texture, WLD, and HOG as well as some popular deep neural networks like InceptionV3, InceptionResNetV2, MobileNet, VGG16 and VGG19.