An Approach for Multi Label Image Classification Using Single Label Convolutional Neural Network

Citations Over Time

Abstract

Single label image classification has been promisingly demonstrated using Convolutional Neural Network (CNN). However, how this CNN will fit for multi-label images is still difficult to solve. It is mainly difficult due to lack of multi-label training image data and high complexity of latent obj ect layouts. This paper proposes an approach for classifying multi-label image by a trained single label classifier using CNN with objectness measure and selective search. We have taken two established image segmentation techniques for segmenting a multi-label image into some segmented images. Then we have forwarded the images to our trained CNN and predicted the labels of the segmented images by generalizing the result. Our single-label image classifier gives 87% accuracy on CIFAR-10 dataset. Using objectness measure with CNN gives us 51 % accuracy on a multi-label dataset and gives up to 57% accuracy using selective search both considering top-4 labels that is significantly good for a simple approach rather than a complex approach for multi-label classification using CNN.

Related Papers

• → Advancements in Image Classification using Convolutional Neural Network(2018)385 cited
• → DCNN-Based Vegetable Image Classification Using Transfer Learning: A Comparative Study(2021)48 cited
• → Research on Clothing Image Classification by Convolutional Neural Networks(2018)5 cited
• → Comparison of different convolutional neural network techniques for car models classification(2023)1 cited