Image Retrieval using Multi Texton Co-occurrence Descriptor and Discrete Wavelet Transform

Minarno, Agus Eko; Sumadi, Fauzi Dwi Setiawan; Munarko, Yuda; Alviansyah, Wayan Yulyo; Azhar, Yufis

doi:10.1109/icoict49345.2020.9166361

Cited by 7 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, the performance of the feature extraction process was improved using the multi-texton histogram (MTH) method using the MTCD method. The results of this study showed an increase in precision of 2.86% for batik data, 2.40% for 5000 Corel data, and 3.06% for 10000 Corel data [8]. Similar research has also been conducted that discusses the redesign of the image retrieval process using the MTCD and K-Nearest Neighbor (KNN) methods using batik and Corel data.…”

Section: Related Researchsupporting

confidence: 54%

“…The results of the 4 textons are then represented in the form of a histogram [19]. Then in the research conducted by Agus Eko, adding 2 textons which are textons from the representation of the MTCD method aims to prevent loss of information, then the textons will work below the horizontal and right vertical [8]. The textons used in MTCD can be seen in Fig.…”

Section: Multi Texton Co-occurrence Descriptor (Mtcd)mentioning

confidence: 99%

See 1 more Smart Citation

Classification of Pringgasela Typical Songket Using Multi Texton Co-occurrence Descriptor and K-Nearest Neighbor

Ilahi¹,

Bimantoro²,

Dwiyansaputra³

et al. 2022

Proceedings of the First Mandalika International Multi-Conference on Science and Engineering 2022, MIMSE 2022 (Informatics and

View full text Add to dashboard Cite

Songket is one of Indonesia's cultural heritages in traditional fabrics that are still preserved today. Pringgasela, a village located on Lombok Island has been producing Songket with distinct characteristics and various patterns. Generally, people are aware of the typical Pringgasela Songket pattern but the difference between one pattern and another is often unrecognized. Furthermore, information regarding the types of Pringgasela Songket has not been well documented. This study aims to build a model that can classify the Pringgalsela Songket patterns using Multi Texton Co-Occurrence Descriptor (MTCD) and K-Nearest Neighbor (KNN) methods. The data used in this study were 4700 images of Pringgasela's Songket, which were divided into training and test data. The highest accuracy obtained was 99.99, 100% precision, and 100% recall with k = 3, using manhattan distance calculation.

show abstract

Section: Related Researchsupporting

confidence: 54%

Section: Multi Texton Co-occurrence Descriptor (Mtcd)mentioning

confidence: 99%

Classification of Pringgasela Typical Songket Using Multi Texton Co-occurrence Descriptor and K-Nearest Neighbor

Ilahi¹,

Bimantoro²,

Dwiyansaputra³

et al. 2022

Proceedings of the First Mandalika International Multi-Conference on Science and Engineering 2022, MIMSE 2022 (Informatics and

View full text Add to dashboard Cite

show abstract

“…Figure 6 depicts the histogram result of GLCM feature extraction in sequential order from the left to the right (angle energy 0 (1), contrast angle 0 (2), entropy of angle 0 (3), correlation angle 0 (4), angle energy 45 (5), angle contrast 45 (6), angle entropy 45 (7), correlation angle 45 (8), angle energy 90 (9), contrast angle 90 (10), entropy angle 90 (11), correlation angle 90 (12), energy angles 135 (13), contrast angles 135 (14), entropy angles 135 (15), and angular correlations 135 ( 16)). The extracted features that have been obtained are applied for the classification process.…”

Section: Figure 2 the Angles In Glcmmentioning

confidence: 99%

“…Nurhida et al [10] compared the performance of the GLCM method, Canny Edge Detection, and Gabor for extraction of batik features, showing that the GLCM method had the best performance with classification accuracy reaching 80%. Minarno et al [11] compared performance for precision and recall among the GLCM method, multi texton histogram (MTH), MTH + GLCM and the multi texton co-occurrence descriptor (MTCD). Meanwhile, Fahrurozi et al [12] combined the GLCM method with several edge detection methods to perform feature extraction on wood fibres.…”

mentioning

confidence: 99%

Classification of batik patterns using K-Nearest neighbor and support vector machine

et al. 2020

Self Cite

View full text Add to dashboard Cite

This study is proposed to compare which are the better method to classify Batik image between K-Nearest neighbor and Support Vector Machine using minimum features of GLCM. The proposed steps are started by converting image to grayscale and extracting colour feature using four features of GLCM. The features include Energy, Entropy, Contras, Correlation and 0o, 45o, 90o, and 135o. The classifier features consist of 16 features in total. In the experimental result, there exist comparison of previous works regarding the classification KNN and SVM using multi texton histogram (MTH). The experiments are carried out in the form of calculation of accuracy with data sharing and cross-validation scenario. From the test results, the average accuracy for KNN is 78.3% and 92.3% for SVM in the cross-validation scenario. The scenario for the highest accuracy of data sharing is at 70% for KNN and at 100% for SVM. Thus, it is apparent that the application of the GLCM and SVM method for extracting and classifying batik motifs has been effective and better than previous work.

show abstract

“…Feature extraction method based on textons has been successfully conducted in Batik image analysis [4][5][6][7][8][9]. Textons are the elements of texture perception proposed by Julez [10].…”

Section: Introductionmentioning

confidence: 99%

Comparison of Methods for Batik Classification Using Multi Texton Histogram

et al. 2018

Self Cite

View full text Add to dashboard Cite

Batik is a symbol reflecting Indonesian culture which has been acknowledged by UNESCO since 2009. Batik has various motifs or patterns. Because most regions in Indonesia have their own characteristic of batik motifs, people find difficulties to recognize the variety of Batik. This study attempts to develop a system that can help people to classify Batik motifs using Multi Texton Histogram (MTH) for feature extraction. Meanwhile, k-Nearest Neighbor (k-NN) and Support Vector Machine (SVM) algorithm were employed for classification. The performance of those classifications is then compared to seek the best classification method for Batik classification. The performance is tested 300 images divided into 50 classes. The results show the optimum accuracy achieved using k-NN with k=5 and MTH with 6 textons is 82%; however, SVM and MTH with 6 textons denote 76%. According to the result, MTH as feature extraction, k-NN or SVM as a classifier can be applied on Batik image classification.

show abstract

Image Retrieval using Multi Texton Co-occurrence Descriptor and Discrete Wavelet Transform

Cited by 7 publications

References 15 publications

Classification of Pringgasela Typical Songket Using Multi Texton Co-occurrence Descriptor and K-Nearest Neighbor

Classification of Pringgasela Typical Songket Using Multi Texton Co-occurrence Descriptor and K-Nearest Neighbor

Classification of batik patterns using K-Nearest neighbor and support vector machine

Comparison of Methods for Batik Classification Using Multi Texton Histogram

Contact Info

Product

Resources

About