Large Scale Linear Coding for Image Classification
نویسندگان
چکیده
Image classification, including object recognition and scene classification, remains to be a major challenge to the computer vision community. As machine can be able to extract information from an image and classify it in order to solve some tasks. Recently SVMs using Spatial Pyramid Matching (SPM) kernel have been highly successful in image classification. Despite its popularity, this technique cannot handle more than thousands of training images. In this paper we develop an extension of the SPM method, by generalizing Vector Quantization to Sparse Coding followed by multi-scale Spatial Max Pooling, and also propose a large scale linear classifier based on Scale Invariant Feature Transform (SIFT) and Sparse Codes. This new adapted algorithm remarkably can handle thousands of training images and classify them into different categories.
منابع مشابه
Face Recognition using an Affine Sparse Coding approach
Sparse coding is an unsupervised method which learns a set of over-complete bases to represent data such as image and video. Sparse coding has increasing attraction for image classification applications in recent years. But in the cases where we have some similar images from different classes, such as face recognition applications, different images may be classified into the same class, and hen...
متن کاملOnline Discriminative Dictionary Learning for Image Classification Based on Block-Coordinate Descent Method
Previous researches have demonstrated that the framework of dictionary learning with sparse coding, in which signals are decomposed as linear combinations of a few atoms of a learned dictionary, is well adept to reconstruction issues. This framework has also been used for discrimination tasks such as image classification. To achieve better performances of classification, experts develop several...
متن کاملHyperspectral Image Classification Based on the Fusion of the Features Generated by Sparse Representation Methods, Linear and Non-linear Transformations
The ability of recording the high resolution spectral signature of earth surface would be the most important feature of hyperspectral sensors. On the other hand, classification of hyperspectral imagery is known as one of the methods to extracting information from these remote sensing data sources. Despite the high potential of hyperspectral images in the information content point of view, there...
متن کاملNoise-Robust Semi-Supervised Learning by Large-Scale Sparse Coding
This paper presents a large-scale sparse coding algorithm to deal with the challenging problem of noiserobust semi-supervised learning over very large data with only few noisy initial labels. By giving an L1-norm formulation of Laplacian regularization directly based upon the manifold structure of the data, we transform noise-robust semi-supervised learning into a generalized sparse coding prob...
متن کاملA Deconvolutional Strategy for Implementing Large Patch Sizes Supports Improved Image Classification
Sparse coding is a widely-used technique for learning an overcomplete basis set from unlabeled image data. We hypothesize that as the size of the image patch spanned by each basis vector increases, the resulting dictionary should encompass a broader range of spatial scales, including more features that better discriminate between object classes. Previous efforts to measure the effects of patch ...
متن کامل