Comparative study of texture detection and classification algorithms

Koltsov, P. P.

doi:10.1134/s0965542511080112

Cited by 7 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Textural features contain information about the spatial distribution of tonal variations within a band [5]. It is used to specify the roughness or coarseness of object surface and described as a pattern with some kinds of regularity, such as the gray level co-occurrence matrixes [6], Markov random field (MRF) model [7] and simultaneous auto-regressive (SAR) model [8]. The features extracted from these patches should give a more discriminated representation of the image, the matter that will lead to better retrieval results.…”

Section: Fig 1: Face Recognition System Phasesmentioning

confidence: 99%

Face Recognition System for Students’ Attendance Register

Mustafa¹,

Amany²,

Elsaeed³

2019

IJCA

View full text Add to dashboard Cite

Face recognition is very important topic because of its applications. The purpose of this work is developing a system that can recognize a person and register postgraduate students' attendance at faculty of specific education, Damietta University, Egypt. The proposed system consists of five stages: image acquisition, face detection, pre-processing, features extraction and classification. Image acquisition to capture real-time images. Face detection to detect face region from the image. Pre-processing stage involve the effective way of suppressing the unwanted distortion of image. Feature

show abstract

Section: Fig 1: Face Recognition System Phasesmentioning

confidence: 99%

Face Recognition System for Students’ Attendance Register

Mustafa¹,

Amany²,

Elsaeed³

2019

IJCA

View full text Add to dashboard Cite

show abstract

“…In the model, based method, a statistical/mathematical model will be used for the denoising. Whereas in Learning based method, an algorithm will be trained by using sufficient parameters and then the model is allowed to work based on its weightage function [8].…”

Section: Introductionmentioning

confidence: 99%

Image Denoising by using Modified SGHP Algorithm

Kollem¹,

Reddy²,

Rao³

2018

IJECE

View full text Add to dashboard Cite

In real time applications, image denoising is a predominant task. This task makes adequate preparation for images looks prominent. But there are several denoising algorithms and every algorithm has its own distinctive attribute based upon different natural images. In this paper, we proposed a perspective that is modified parameter in S-Gradient Histogram Preservation denoising method. S-Gradient Histogram Preservation is a method to compute the structure gradient histogram from the noisy observation by taking different noise standard deviations of different images. The performance of this method is enumerated in terms of peak signal to noise ratio and structural similarity index of a particular image. In this paper, mainly focus on peak signal to noise ratio, structural similarity index, noise estimation and a measure of structure gradient histogram of a given image.

show abstract