SuperPixel Based Angular Differences as a Mid-level Image Descriptor

Abstract

This paper focuses on the object recognition task and aims at improving the accuracy with an emphasis on the feature extraction step. Feature extraction is widely used in image classification as an initial step in the pipeline. In this paper, we propose a method to explore the conventional feature extraction techniques from the perspective that mid-level information could be incorporated in order to obtain a superior scene description. We hypothesize that the commonly used pixel based low-level descriptions are useful but can be improved with the introduction of mid-level region information. Hence, we investigate superpixel based image representation to acquire such mid-level information in order to improve the classification accuracy. Detailed experimental evaluations on classification and retrieval tasks are performed in order to validate the proposed hypothesis. A consistent increase is observed in the mean average precision (MAP) score for different experimental scenarios and image categories.

SSNet: Learning Mid-Level Image Representation Using Salient Superpixel Network

“…In addition, the research [7,28] obtains the mid-level representation by pooling more discriminative information than the standard BoVW model does. Ronan Sicre et al [29] propose a novel descriptor that encapsulates the mid-level information based on superpixel structure. Yuan et al [30] generate visual phrases via combining the visual words depending on the co-occurrence of them.…”

“…So, for the WSOAP, based on the properties of the Riemannian manifold [56], we map it to the Euclidean tangent space by using the Log-Euclidean metrics, i.e., WSOAP logm = log m (WSOAP). (29) Here, the result WSOAP logm is still a symmetric matrix. To the WSOMP, the power normalization mapping [50] is adopted, which is able to further reduce the influence of the burstiness.…”

Identity Documents Classification as an Image Classification Problem

“…It is worth mentioning that other approaches have been proposed in Computer Vision with the aim to build mid-level description [29] or to learn a set 1 , Ahmad Montaser Awal 2 , and Teddy Furon of discriminative parts to model classes [10,28,25]. They are highly effective in similar fine-grain classification scenarios but are extremely costly.…”

Discovering and Aligning Discriminative Mid-level Features for Image Classification

“…We observe three mains trends on mid-level description in the recent literature: hand crafted, learned, and unsupervised features. Hand crafted mid-level features aim at encapsulating information on groups of pixel such as superpixels [16], [17], patches [18] or segments [19]. These descriptors are computed similarly for any given image and do not require any learning.…”