Approaches of large-scale images recognition with more than 50,000 categoris

TL;DR

This paper presents a practical approach combining traditional computer vision techniques with neural networks to classify large-scale datasets with over 50,000 categories efficiently in terms of time and memory.

Contribution

It introduces methods to optimize large-scale image classification, integrating traditional CV and neural networks, and addresses challenges like data mislabeling and resource constraints.

Findings

Achieved classification on large datasets using limited hardware

Optimized traditional CV techniques for large-scale data

Reduced impact of mislabeling in large datasets

Abstract

Though current CV models have been able to achieve high levels of accuracy on small-scale images classification dataset with hundreds or thousands of categories, many models become infeasible in computational or space consumption when it comes to large-scale dataset with more than 50,000 categories. In this paper, we provide a viable solution for classifying large-scale species datasets using traditional CV techniques such as.features extraction and processing, BOVW(Bag of Visual Words) and some statistical learning technics like Mini-Batch K-Means,SVM which are used in our works. And then mixed with a neural network model. When applying these techniques, we have done some optimization in time and memory consumption, so that it can be feasible for large-scale dataset. And we also use some technics to reduce the impact of mislabeling data. We use a dataset with more than 50, 000 categories, and all operations are done on common computer with l 6GB RAM and a CPU of 3. OGHz. Our contributions are: 1) analysis what problems may meet in the training processes, and presents several feasible ways to solve these problems. 2) Make traditional CV models combined with neural network models provide some feasible scenarios for training large-scale classified datasets within the constraints of time and spatial resources.