Classification of breast tissue images based on wavelet transform using discriminant analysis, neural network and SVM

Hwang, Hae-Gil; Choi, Hee Kyoung; Kang, Byoung-Doo; Yoon, Hye-Kyoung; Kim, Hee Cheol; Kim, Sang-Kyoon; Choi, Heung‐Kook

doi:10.1109/health.2005.1500478

Cited by 3 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies regarding mammographic mass detection and classification were introduced recently (Andre & Rangayyan, ; Youssry et al ., ; Chen & Chang, ; Hwang et al ., ; Binh & Thanh, ; Acharya et al ., ; Dominguez & Nandi, ; Karahaliou et al ., ; Lladó et al ., ; Zeng & Liu, ; Liu et al ., ). However, there are fewer studies related to curvelet and spherical wavelet transform (SWT) than those related to discrete wavelet transform (DWT).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Computer‐aided classification of breast masses in mammogram images based on spherical wavelet transform and support vector machines

2014

View full text Add to dashboard Cite

Breast cancer can be effectively detected and diagnosed using the technology of digital mammography. However, although this technology has been rapidly developing recently, suspicious regions cannot be detected in some cases by radiologists, because of the noise or inappropriate mammogram contrast. This study presents a classification of segmented region of interests (ROIs) as either benign or malignant to serve as a second eye of the radiologists. Our study consists of three steps. In the first step, spherical wavelet transform (SWT) is applied to the original ROIs. In the second step, shape, boundary and grey level based features of wavelet (detail) and scaling (approximation) coefficients are extracted. Finally, in the third step, malignant/benign classification of the masses is implemented by giving the feature matrices to a support vector machine system. The proposed system achieves 91.4% and 90.1% classification accuracy using the dataset acquired from the hospital of Istanbul University in Turkey and the free Mammographic Image Analysis Society, respectively. Furthermore, discrete wavelet transform, which produces 83.3% classification accuracy, is applied to the coefficients to make a comparison with the SWT method.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Hwang et al . () used Haar wavelet transform for pre‐processing and extracted texture features of the mammograms. They also used statistical discriminant analysis, neural networks and support vector machine (SVM) in the classification step.…”

Section: Introductionmentioning

confidence: 99%

Computer‐aided classification of breast masses in mammogram images based on spherical wavelet transform and support vector machines

2014

View full text Add to dashboard Cite

show abstract

“…This paper introduces a novel framework for tissue image classification and retrieval that uses the multi-fractal property of the images. Tissue image classification has been previously attempted using techniques such as wavelet transforms and discriminant analysis (Hwang et al, 2005;Aksoy et al, 2002). Our paper proposes a completely different approach, and presents two new texture feature descriptors: one constructed from the histogram of Holder exponents in the image, and the second from the geometrical properties of the multi-fractal spectra.…”

Section: Introductionmentioning

confidence: 99%

Tissue Image Classification Using Multi-Fractal Spectra

Hemsley

Mukundan

2010

International Journal of Multimedia Data Engineering and Management

View full text Add to dashboard Cite

Tissue image classification is a challenging problem due to the fact that the images contain highly irregular shapes in complex spatial arrangement. The multi-fractal formalism has been found useful in characterizing the intensity distribution present in such images, as it can effectively resolve local densities and also represent various structures present in the image. This paper presents a detailed study of feature vectors derived from the distribution of Holder exponents and the geometrical characteristics of the multi-fractal spectra that can be used in applications requiring image classification and retrieval. The paper also gives the results of experimental analysis performed using a tissue image database and demonstrates the effectiveness of the proposed multi-fractal-based descriptors in tissue image classification and retrieval. Implementation aspects that need to be considered for improving classification accuracy and the feature representation capability of the proposed descriptors are also outlined.

show abstract

Feature extraction of sewer pipe failures by wavelet transform and co-occurrence matrix

Yang

Pan

et al. 2008

2008 International Conference on Wavelet Analysis and Pattern Recognition

View full text Add to dashboard Cite

Traditionally, the sewer inspection usually discovers sewer failures on numerous CCTV images by human interpretation. However, it remains to be improved in both consideration of economic and efficient due to human's fatigue and subjectivity. To enhance the sewer inspection approaches, this paper attends to employ artificial intelligence into image process to extract the failure features of the sewer systems, which was also applied to the sewer system in the eastern Taichung City, Taiwan. The extracted features are valuable information in pattern recognition of failures on CCTV images. Wavelet transform and gray-level co-occurrence matrix, which have been widely applied in many texture analyses. were adopted in this research. Wavelet transform is capable of dividing an image into four sub-images including approximation sub-image, horizontal detail sub-image, vertical detail sub-image, and diagonal detail sub-image. In this paper, the co-occurrence matrixes of horizontal orientation, vertical orientation, and 45 。 and 135 。 orientations, respectively, were calculated for the horizontal, vertical, and diagonal detail sub-images. Subsequently, the features including angular second moment, entropy, contrast, homogeneity, dissimilarity, correlation, and cluster tendency, can be obtained from the co-occurrence matrixes. However, redundant features either could decrease the accuracy of texture description or could increase the difficulty of pattern recognition. Thus, the correlations of the features are estimated to find out the appropriate feature sets in which the coefficients of correlation of the features are less than 0.5. Finally, a discriminant analysis was used to evaluate their discriminabilities to the pipe defect patterns, and entropy, correlation, and cluster tendency were the best feature vector because of its better discriminant accuracy according error matrix analysis.

show abstract

Classification of breast tissue images based on wavelet transform using discriminant analysis, neural network and SVM

Cited by 3 publications

References 17 publications

Computer‐aided classification of breast masses in mammogram images based on spherical wavelet transform and support vector machines

Computer‐aided classification of breast masses in mammogram images based on spherical wavelet transform and support vector machines

Tissue Image Classification Using Multi-Fractal Spectra

Feature extraction of sewer pipe failures by wavelet transform and co-occurrence matrix

Contact Info

Product

Resources

About