Pixel classification based color image segmentation using quaternion exponent moments

Wang, Xiangyang; Wu, Zhiyong; Chen, Liang; Hong-liang, Zheng; Yang, Heng

doi:10.1016/j.neunet.2015.10.012

Cited by 25 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We opted to use SVM since SVM-based classifiers achieve higher overall accuracies and lower variability when used with different training datasets relative to other methods such as neural networks and classification and regression trees. 28,36 Since the makeup of an SVM is not part of our contribution, we refer you to the work of Burges 37 for a full and clear description of its operation. The SVM program we used comes from the Weka machine learning software package developed by Witten et al, 38…”

Section: From Training Instances To Trained Classifiermentioning

confidence: 99%

“…Based on these factors, a set of coefficients are calculated to describe the spatial information in the neighborhood. There are other methods that utilize algebraic systems such as the work of Wang et al Here, the authors used quaternion exponent moments in combination with twin SVMs to have an image segmented, pixelwise. A notable weakness of this method is its high computational expense.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptable image segmentation via simple pixel classification

Kharma

Mazhurin²,

Saigol

et al. 2018

Computational Intelligence

View full text Add to dashboard Cite

We propose an approach to image segmentation that views it as one of pixel classification using simple features defined over the local neighborhood. We use a support vector machine for pixel classification, making the approach automatically adaptable to a large number of image segmentation applications. Since our approach utilizes only local information for classification, both training and application of the image segmentor can be done on a distributed computing platform. This makes our approach scalable to larger images than the ones tested. This article describes the methodology in detail and tests it efficacy against 5 other comparable segmentation methods on 2 well‐known image segmentation databases. Hence, we present the results together with the analysis that support the following conclusions: (i) the approach is as effective, and often better than its studied competitors; (ii) the approach suffers from very little overfitting and hence generalizes well to unseen images; (iii) the trained image segmentation program can be run on a distributed computing environment, resulting in linear scalability characteristics. The overall message of this paper is that using a strong classifier with simple pixel‐centered features gives as good or better segmentation results than some sophisticated competitors and does so in a computationally scalable fashion.

show abstract

Section: From Training Instances To Trained Classifiermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Adaptable image segmentation via simple pixel classification

Kharma

Mazhurin²,

Saigol

et al. 2018

Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…At an early stage, most of the image processing algorithms for PRKbS have to deal with a segmentation step [57][58][59] , which refers to the analysis of the input signal aiming to highlight meaningful areas of interest. Usually, such a process is based on border extraction, a strategy that identifies the pixels responsible for defining the boundaries between objects or specific parts of the image.…”

Section: Image Analysis and Re-synthesis For Border Extractionmentioning

confidence: 99%

ZCR-aided neurocomputing: A study with applications

Guido

2016

Knowledge-Based Systems

View full text Add to dashboard Cite

This paper covers a particular area of interest in pattern recognition and knowledge-based systems (PRKbS), being intended for both young researchers and academic professionals who are looking for a polished and refined material. Its aim, playing the role of a tutorial that introduces three feature extraction (FE) approaches based on zero-crossing rates (ZCRs), is to offer cutting-edge algorithms in which clarity and creativity are predominant. The theory, smoothly shown and accompanied by numerical examples, innovatively characterises ZCRs as being neurocomputing agents. Source-codes in C/C++ programming language and interesting applications on speech segmentation, image border extraction and biomedical signal analysis complement the text.

show abstract

“…The most important factors that help clinicians to classify hyperemia are degree of redness, hue of the colour and location of the vasodilation [1]. The accurate interpretation of bulbar redness can identify various pathologies like morning eye congestion, bacterial conjunctivitis, dry eye [2], trauma due to prolonged use of contact lenses, iritis and other severe infections [1] [3]. It is also a well know side effect of glaucoma treatment [4].Because of these symptoms, patients suffering from the glaucoma drugs often discontinue the treatment [5].Timely and correct diagnosis of these conditions can further reduce any damage to the eye and also help in treatment plan.…”

Section: Introductionmentioning

confidence: 99%

Classifying Red and Healthy Eyes using Deep Learning

Verma¹,

Singh²,

Chaudhry³

2019

IJACSA

View full text Add to dashboard Cite

Eye is one of the most vital organs of human body. Despite being small in size, humans cannot see the life around them without it. Human eye is protected by a thin covering termed as conjunctiva which protects the eye from dust particles. It plays the role of lubricant in the eye which prevents any sort of friction in opening and closing of eye. Broadly there are two kinds of conjunctiva: bulbar and palpebral. The membrane covering the inner portion of eyelids is termed as palpebral conjunctiva and the one covering the outside portion of the eye is called as bulbar conjunctiva (white portion of eye).Due to the dilation of blood vessels the white portion of the eye also termed as sclera becomes red in color. This condition is also termed as hyperemia. The study of this development is vital in diagnosis of various pathologies. It could be result of some trauma, injury or other eye related diseases which needs to be identified for timely treatment. Enormous amount of studies have been done to study the structure and functionality of human eye. This paper highlights the work done so far for measuring the level of redness in the eye using various methodologies ranging from statistical ways to machine learning techniques and proposes a methodology using Matlab and Convolutional neural network to automate this evaluation process.

show abstract

Pixel classification based color image segmentation using quaternion exponent moments

Cited by 25 publications

References 37 publications

Adaptable image segmentation via simple pixel classification

Adaptable image segmentation via simple pixel classification

ZCR-aided neurocomputing: A study with applications

Classifying Red and Healthy Eyes using Deep Learning

Contact Info

Product

Resources

About