Similarity measures play crucial role in Content-Based Dermoscopic Image Retrieval (CBDIR). This paper analyses and compares images based respectively on twelve distances namely: Minkowski, Euclidean, Standardized Euclidean, Mahalanobis, Manhattan, Chebychev, Cosine, Canberra, Relative Deviation, Bray-Curtis, Square Chord and Square Chi-Squared measures for CBDIR. Two dermatologists were asked to diagnose 176 skin lesion images in order to classify them. Eight common classes of pigmented skin lesions have been identified, including: Melanoma, Nevus/Mole (ML), Lentigo (Len), Basal Cell Carcinoma (BCC), Seborrhoeic Keratosis (SK), Actinic Keratosis (AK), Angioma (AG) and Dermatofibroma (DF). Color and texture features have been extracted from the segmented skin lesions. Then a series of CBDIR experiments were conducted on the image database. The results indicate that the CBDIR performance is significantly improved by using Canberra and Bray-Curtis distances compared to conventional measures.
K. Belattar and S. Mostefai. 2015. Similarity measures for Content-Based Dermoscopic Image Retrieval: A comparative study. In Proceedings of the 1st International Conference on New Technologies of Information and Communication (NTIC'15), Mila, Algeria (November 2015), IEEE, 1-6. DOI: https://doi.org/10.1109/NTIC.2015.7368761.
APA :
Belattar, K. & Mostefai, S. (2015, November). Similarity measures for Content-Based Dermoscopic Image Retrieval: A comparative study. In Proceedings of the 1st International Conference on New Technologies of Information and Communication (NTIC'15), Mila, Algeria, IEEE, 1-6. DOI: https://doi.org/10.1109/NTIC.2015.7368761
IEEE :
K. Belattar and S. Mostefai, "Similarity measures for Content-Based Dermoscopic Image Retrieval: A comparative study". In Proceedings of the 1st International Conference on New Technologies of Information and Communication (NTIC'15), Mila, Algeria, IEEE, pp. 1-6, November, 2015. DOI: https://doi.org/10.1109/NTIC.2015.7368761.
BibTeX :
@inproceedings{misc-lab-239, author = {Belattar, Khadidja and Mostefai, Sihem}, title = {Similarity measures for Content-Based Dermoscopic Image Retrieval: A comparative study}, booktitle = {1st International Conference on New Technologies of Information and Communication (NTIC'15)}, location = {Mila, Algeria}, isbn = {978-1-4673-6684-7}, pages = {1--6}, publisher = {IEEE}, year = {2015}, month = {November}, doi = {10.1109/NTIC.2015.7368761}, url = {https://ieeexplore.ieee.org/abstract/document/7368761}, keywords = {content-based retrieval, image classification, image colour analysis, image retrieval, image segmentation, image texture, medical image processing} }
RIS :
TY - CONF TI - Similarity measures for Content-Based Dermoscopic Image Retrieval: A comparative study AU - K. Belattar AU - S. Mostefai PY - 2015 BT - 1st International Conference on New Technologies of Information and Communication (NTIC'15), Mila, Algeria SN - 978-1-4673-6684-7 SP - 1 EP - 6 PB - IEEE AB - Similarity measures play crucial role in Content-Based Dermoscopic Image Retrieval (CBDIR). This paper analyses and compares images based respectively on twelve distances namely: Minkowski, Euclidean, Standardized Euclidean, Mahalanobis, Manhattan, Chebychev, Cosine, Canberra, Relative Deviation, Bray-Curtis, Square Chord and Square Chi-Squared measures for CBDIR. Two dermatologists were asked to diagnose 176 skin lesion images in order to classify them. Eight common classes of pigmented skin lesions have been identified, including: Melanoma, Nevus/Mole (ML), Lentigo (Len), Basal Cell Carcinoma (BCC), Seborrhoeic Keratosis (SK), Actinic Keratosis (AK), Angioma (AG) and Dermatofibroma (DF). Color and texture features have been extracted from the segmented skin lesions. Then a series of CBDIR experiments were conducted on the image database. The results indicate that the CBDIR performance is significantly improved by using Canberra and Bray-Curtis distances compared to conventional measures. KW - content-based retrieval KW - image classification KW - image colour analysis KW - image retrieval KW - image segmentation KW - image texture KW - medical image processing DO - 10.1109/NTIC.2015.7368761 UR - https://ieeexplore.ieee.org/abstract/document/7368761 ID - misc-lab-239 ER -