A New Approach to Texture Recognition Using Decorrelation Stretching

Kalfon, Micha; Porat, Moshe

doi:10.7763/ijfcc.2013.v2.119

Cited by 6 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To prepare the quality biopsy image dataset the pre-processing step involves a multiple personality behavioural image processing technique called decorrelation stretching and also known as decorrelation contrast stretching (decor). A decorrelation stretching technique is incorporated with PCA in order to preserve the edges of the spectral images and to retain the geometrical features of the images [15,16].…”

Section: Stain Normalization and Background Deductionmentioning

confidence: 99%

Severity Grade Recognition for Nasal Cavity Tumours Using D閏or CNN

Mathialagan¹,

Malathy²

2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Nasal cavity and paranasal sinus tumours that occur in the respiratory tract are the most life-threatening disease in the world. The human respiratory tract has many sites which has different mucosal lining like frontal, parred, sphenoid and ethmoid sinuses. Nasal cavity tumours can occur at any different mucosal linings and chances of prognosis possibility from one nasal cavity site to another site is very high. The paranasal sinus tumours can metastases to oral cavity and digestive tracts may lead to excessive survival complications. Grading the respiratory tract tumours with dysplasia cases are more challenging using manual pathological procedures. Manual microscopic biopsy tissue analysis is time consuming and chances of occurring interobserver variability problems are very high. To avoid nasal cavity tumour grade misclassification a State-Of-The-Art Automated Décor CNN model is proposed. The automated nasal cavity tumour grading classification model is designed to troubleshoot the stain artifact present in the biopsy tissue samples. Major nasal cavity sites are analysed to find the abnormal epithelium. The automated morphological characteristic findings with décor CNN model in biopsy images are promising. The model achieves the classification accuracy of 98% with less training, testing and validation errors compared to other transfer learning convolution neural network models.

show abstract

Section: Stain Normalization and Background Deductionmentioning

confidence: 99%

Severity Grade Recognition for Nasal Cavity Tumours Using D閏or CNN

Mathialagan¹,

Malathy²

2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

show abstract

“…The performance has been evaluated for direct visual inspection and quantitative analysis of glioma, meningioma, and pituitary tumors. The proposed method is compared with CLAHE with Median filter [46], CLAHE with Wiener filter [25], Decorrelation [47], Enhancement Gravitational Search Algorithm (EnhGSA) [48], Median Mean based Sub Image Clipped Histogram Equalization (MMSICHE) [49], Variational based Fusion model for Gray Scale image Enhancement (VFGLE) [50], and Bi-Histogram Equalization with Adaptive Sigmoid Function (BEASF) [40]. The visual comparison of the proposed method with other state-of-the-art methods by taking an image from three different type of tumors, shown in Figure 1.…”

Section: Figure 1 Visual Analysis Of Original and Enhanced Imagesmentioning

confidence: 99%

An Approach for Enhancement of MR Images of Brain Tumor

Mishra¹,

Kaur²

2022

View full text Add to dashboard Cite

Magnetic Resonance Imaging plays an important role in diagnosing the brain tumor accurately, but it requires the approach to enhance the magnetic resonance images to assist physicians in brain tumor detection and making the treatment plan precisely to reduce the mortality rate. Therefore, in this proposed work, a comprehensive learning-based elephant herding optimization technique has been introduced to select the optimal value of smoothness factor in Bi-Histogram Equalization with Adaptive Sigmoid Function that enhances the visual quality as well as the appearance of the suspicious regions in magnetic resonance images. Further, the enhancement performance has been evaluated by the enhancement quality metrics. The metrics used include mean square error, peak signal to noise ratio, mean absolute error, structural similarity index metric, feature similarity index metric, Riesz transformed based feature similarity index metric, spectral residual-based similarity index metric, and absolute mean brightness error. The outcomes of this proposed work have a remarkable impact on enhancing magnetic resonance images and providing visual assistance for diagnosing brain tumors. The performance of the evaluation metrics is verified with Friedman's mean rank test, which strongly indicates a statistical difference between the proposed method and state-of-the-art methods.

show abstract

“…Accordingly, the same décor technique is used to remove unwanted background details by applying normalization technique on each RGB colour channel alternately is shown in section 3.2.1.1. The decorrelation stretching technique is used to improve the colour channels with high intensity and to highlight each pixel by stretching its colour contrasts [24]. Sample biopsy image before and after contrast stretching is shown in figure 3.…”

Section: Stain Normalization and Background Separationmentioning

confidence: 99%

Analysis and Classification of H&E-Stained Oral Cavity Tumour Gradings Using Convolution Neural Network

Mathialagan¹

2021

IJIES

View full text Add to dashboard Cite

Upper Aero Digestive Tract (UADT) cancer is one of the most common cancer types in any gender. Early detection and diagnosing such type of cancer will reduce the risk of death in human. In this paper we addressed the state-of-the-art solutions for two major pathological constraints like, dysplasia type tumour grading and tumour grade classification with artifact's present in biopsy images. A new Whole Slide and patch-based CNN model was proposed which involves different pre-processing techniques to detect and normalize the stain artifacts present in biopsy tissue samples. The proposed CNN model is developed to classify different oral cavity tumour sites and its gradings automatically. It was observed that the proposed CNN model achieved best accuracy of 98 % with zero classification error rate. These findings will throw a light for pathologists to handle digital biopsy images with artifacts and also will classify dysplasia type tumour grades automatically.

show abstract

A New Approach to Texture Recognition Using Decorrelation Stretching

Cited by 6 publications

References 13 publications

Severity Grade Recognition for Nasal Cavity Tumours Using D閏or CNN

Severity Grade Recognition for Nasal Cavity Tumours Using D閏or CNN

An Approach for Enhancement of MR Images of Brain Tumor

Analysis and Classification of H&E-Stained Oral Cavity Tumour Gradings Using Convolution Neural Network

Contact Info

Product

Resources

About