Batik Image Research Articles

Literature Study of Convolutional Neural Network Algorithm for Batik Classification

Batik is a hereditary cultural heritage that has high aesthetic value and deep philosophy. Currently, Indonesian batik has various types of different motifs and patterns, which are spread in Indonesia with their names and meanings. Batik classification uses Convolutional Neural Network as a pattern recognition method, especially batik image classification. The method used is a literature study, looking at studies from several journals regarding the Convolutional Neural Network Algorithm in Classification and providing conclusions about the usefulness of the algorithm. Analysis This literature study analyzes each journal from previous research related to the Convolutional Neural Network Algorithm in classifying Batik. The results of the analysis, conducted a discussion to better know the characteristics and application of Convolutional Neural Network in the classification of Batik. After discussing, this analysis ends with conclusions about the Convolutional Neural Network algorithm in classifying Batik. Based on previous studies, it can be seen that the convolution neural network can work well for image classification with large datasets. By evaluating the method that has been described by considering the architecture and the level of accuracy, namely getting an accuracy level of 100% with an image size of 128 x 128 and regarding the classification of batik, it shows that image size, image quality, image patterns affect the batik classification process.

Ensemble convolutional neural network for robust batik classification

Some researchers propose using the Convolutional Neural Network (CNN) method to classified batik images. It can extract features automatically without the need to define feature manually from the image. However, CNN’s weakness is that its accuracy is quite low, especially for small-sized datasets, compared to machine learning methods that use handcrafted feature extraction. In this research, an ensemble CNN method is proposed to improve the accuracy of the CNN method in classifying batik images. This method will train several CNN models at once, and then by voting and averaging techniques, the output label will be determined. Test results for two different datasets show this method can improve the accuracy of the CNN method and get an accuracy value of 100%. This method is also proven to extract features faster than the state-of-the-art method like MTCD+SVM, which is included in the hand-crafted feature extraction category.

Graph Extraction of Batik Image Using Region Adjacency Graph Representation

Image feature extraction done in image analysis based on the traditional pixel is not extracted effectively. This is due to the extraction that only represents the content. A very promising approach and the challenge are to extract a graph from an image that represents the content and their relationship. The results of graph extraction are obtained from the process of image segmentation. The selection of an appropriate segmentation method from many graph-based image segmentation methods is interesting to be reviewed. The method of super-pixel segmentation is one way to divide the image into regions. The regions obtained in segmentation are represented by vertices and edges represent connections between adjacent regions. This representation is called Region Adjacency Graph (RAG). In this paper, graph extraction of “batik” images has been successfully performed where its representation uses RAG and segmentation uses the Minimum Spanning Tree method. The results of graph extraction have been tested in a simple image retrieval process using the VF2 graph matching method.

A Combination of Block-Based Chaos with Dynamic Iteration Pattern and Stream Cipher for Color Image Encryption

This research proposes an encryption method on images using a combination of chaotic methods, streams, and hash functions. SHA-1 is used as a hash function to encrypt key inputs to be more secure and can produce more dynamic keys at chaotic and stream encryption stages. Chaos encryption is done by dividing the image into small blocks where each encrypted block differs based on a dynamic key pattern based on chaotic keys. At the last stage, all blocks are made as whole images again to be encrypted by the stream method. Tests carried out on standard RGB images and Indonesian batik images. Encryption quality measurements using entropy, histogram analysis, UACI, NPCR, SSIM, PSNR, and the avalanche effect. Based on the results of trials the proposed method is proven to be resistant to various attacks such as statistics as evidenced by the average entropy value of 7.9996, avalanche effect value of 50.0366 and a relatively uniform histogram, while differential attack as evidenced by the value of UACI 33.5716 and NPCR 99.6082 where this value is very close to ideal. Also visually the results of the encryption look very chaotic and very different from the original image, which is evidenced by the value of PSNR 8.0191 and SSIM 0.0081. The decryption process can also be done perfectly wherein the resulting infinity value on PSNR and value 1 on SSIM.

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

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.

Batik image retrieval using convolutional neural network

This paper presents a simple technique for performing Batik image retrieval using the Convolutional Neural Network (CNN) approach. Two CNN models, i.e. supervised and unsupervised learning approach, are considered to perform end-to-end feature extraction in order to describe the content of Batik image. The distance metrics measure the similarity between the query and target images in database based on the feature generated from CNN architecture. As reported in the experimental section, the proposed supervised CNN model achieves better performance compared to unsupervised CNN in the Batik image retrieval system. In addition, image feature composed from the proposed CNN model yields better performance compared to that of the handcrafted feature descriptor. Yet, it demonstrates the superiority performance of deep learning-based approach in the Batik image retrieval system.

Batik Classification using Deep Learning

Batik is one of the Indonesian cultural heritages that has been recognized by the global community. Indonesian batik has a vast diversity in motifs that illustrate the philosophy of life, the ancestral heritage and also reflects the origin of batik itself. Because of the manybatik motifs, problems arise in determining the type of batik itself. Therefore, we need a classification method that can classify various batik motifs automatically based on the batik images. The technique of image classification that is used widely now is deep learning method. This technique has been proven of its capacity in identifying images in high accuracy. Architecture that is widely used for the image data analysis is Convolutional Neural Network (CNN) because this architecture is able to detect and recognize objects in an image. This workproposes to use the method of CNN and VGG architecture that have been modified to overcome the problems of classification of the batik motifs. Experiments of using 2.448 batik images from 5 classes of batik motifs showed that the proposed model has successfully achieved an accuracy of 96.30%.

Identification of Pekalongan Batik Images Using Backpropagation Method

Batik is an Indonesian cultural heritage that was recognized by UNESCO in 2009. One of the famous batik producing regions in Indonesia is Pekalongan City, Central Java. Pekalongan Batik has a distinctive characteristic compared to other regions, namely from the aspect of color and motif. Pekalongan batik uses bright colors and flora motifs. However, there are some batik craftsmen who still use dark colors. Identify Pekalongan’s typical batik motifs become an obstacle for tourists that are visiting Indonesia. There needs to be an automatic identification system to recognize Pekalongan Batik motifs. The automatic identification system of batik images can contribute to the development of technology in the field of artificial intelligence. This research was conducted by collecting image data taken through observation, interviews and literature review. The image data obtained are four batik motifs. 5 images will be taken from each motif and will be implemented into the system using Matlab R2014a. The next process is feature extraction using the Gray Level Co-Occurrence Matrix (GLCM) method to get information in the batik image. The author then identifies image using the Backpropagation method to obtain the epoch value, learning rate, and accuracy value based on the identification process. The tested system obtained the highest accuracy of 91.2% with epoch 100 and learning rate 0.03 on Sogan batik, 89.6% accuracy with epoch 100 and learning rate 0.02 on Jlamprang batik. 87.2% accuracy was obtained from Cap Kombinasi batik and Tiga Negeri batik with epoch 100, the learning rate was 0.01 and 0.04 respectively. The results of identifying images of Pekalongan batik can be implemented in a more interactive application.

Application System for Identification of Surakarta Traditional Batik Images (SABATARA)

Surakarta Batik is a traditional cloth in Indonesia that has been designated as an intangible cultural heritage by the Ministry of Education and Culture. The Surakarta Batik Pattern has characteristics and has a story in each style. The method used affects the accuracy of each pattern in the Surakarta batik image. Image data used for training data are 100 image data with a size of 256 x 256 pixels, with test image data used as many as 20 image data. Improving the quality of the image using contrast stretching, the output is processed to separate objects with the background using adaptive thresholding. The obtained object is added by the canny process and calculated using the Gray Level Co-Occurrence Matrix to obtain the characteristics of each image. The characteristics used are four variables (energy, contrast, homogeneity, and correlation). The resulting variable is used as input to the classification using backpropagation. The test results obtained an accuracy rate of 95%, with an error rate of 0.05%.

Closed Beta Testing on e-Label Batik Application to Know the Best Environment for Optimal Application Performance

—The Batik of Pekalongan is a heritage that continues to be maintained and until now it is still used as a source of livelihood for the majority of the people in Pekalongan city, so the city of Pekalongan is known as the city of batik. However, the existence of batik is facing a serious threat, caused by the abundance of textile products with batik motifs (batik printing) on the market, but not matched by increased public knowledge of batik. Various efforts, both in Pekalongan city government through the labeling of batik, and ASEPHI in Pekalongan city through the implementation of original batik hologram, has been done to maintain the sustainability of batik. But this has not yet provided optimal results, because it is still found that the fraudulent batik seller who put the original batik label/hologram on batik printing, thus harming the society, harming batik craftsmen/producers and tarnish the batik image of Pekalongan city. This happened because the batik label or the original batik hologram had not been connected to a computer-based information system, so that they cannot monitor and validate the attachment of original batik labels/holograms. For this reason, researchers developed a e-label batik application that was able to be used by the community to scan batik labels that produced by the e-label batik application, so that can know information the authenticity of the batik. The application is also equipped with facilities that provide convenience to monitor, validate, get feedback from the community and become a learning media for the community towards batik. The development of e-label batik applications has gone through the stages of alpha testing and continued with closed beta testing to find out the ideal environment, So that the performance of the batik elabel application is optimal, and can be used properly by the community.

Texture Feature Extraction for Batik Images Using GLCM and GLRLM with Neural Network Classification

Batik has a vast variety of motifs and colors. Aside from its popularity as being part of Indonesian culture, it has become the source of Indonesia’s income. Batik was more promising in the past years for the business opportunities. Batik has economic and high export value as the commodity. Batik has become the main part of national culture; however there is a lack of understanding for many people, as they are still unaware about batik motifs and patterns. Therefore, it is needed for building a model to identify batik motifs. This study aims to combine the features of texture and the feature of shapes’ ornament in batik to classify images using artificial neural networks. The value of texture features of images in batik is extracted using gray level co-occurrence matrices (GLCM) which include Contrast, Correlation, Homogeneity and Energy. And include the Gray level Run length matrices (GLRLM) which includes Gray Level Non-Uniformity (GLN), Long Run Emphasis (LRE), Short Run Emphasis (SRE), Run Percentage (RP). At this phase of the training and testing, we compare the value of a classification accuracy of neural networks in each class in batik with their texture features, and the combination of GLCM and GLRLM. From the three features used in the classification of batik image with artificial neural networks it includes Probabilistic Neural network, it was obtained that GLCM feature has the lowest accuracy rate of 78% and the combination of GLCM and GLRLM features produces a greater value of accuracy by 84%. The results obtained in this study indicate that there is an increase in accuracy of batik image classification using the probabilistic neural network with the combination of GLCM and GLRLM features in batik image.

Re-Ranking Image Retrieval on Multi Texton Co-Occurrence Descriptor Using K-Nearest Neighbor

Some features commonly used to conduct image retrieval are color, texture and edge. Multi Texton Co-Occurrence Descriptor (MTCD) is a method which uses all three features to perform image retrieval. This method has a high precision when doing retrieval on a patterned image such as Batik images. However, for images focusing on object detection like corel images, its precision decreases. This study proposes the use of KNN method to improve the precision of MTCD method by re-ranking the retrieval results from MTCD. The results show that the method is able to increase the precision by 0.8% for Batik images and 9% for corel images.

Batik Image Retrieval System Using Self Organizing Map

This paper describes an image retrieval system for batik motifs from Yogyakarta, Solo, and Lasem region using self organizing map method. The system receives user-uploaded batik image and returns 10 images of batik from Yogyakarta, Solo, and Lasem from the database with the closest distance that is computed using self organizing map. The experiments cluster the batik images into 13 clusters based on the 16 features extracted using gray level co-occurrence matrices (GLCM) to represent the texture of batik. In addition, color moment features are also considered as feature extractor to represent the color values of batik images. The average precision and recall for the experiments with both GLCM and color moment features are 0.5 and 0.082, respectively. Meanwhile, using only GLCM gives the result of 0.377 average precision and 0.060 average recall.

Comparison of Methods for Batik Classification Using Multi Texton Histogram

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.

Implementation of GLCM for Features Extraction and Selection of Batik Images

Batik is a craft that has high artistic value and has been a part of Indonesian culture (especially Java) for a long time. Batik cloth in Indonesia has various types of batik textures, batik cloth colors, and batik fabric patterns that reflect the regional origins of the batik cloth. Regarding the image of batik, the texture feature is an important feature because the ornaments on the batik cloth can be seen as different texture compositions. Besides batik motifs, also influenced by the shape characteristics that become parts of each batik motif. This research will add insight and knowledge to understand batik patterns based on the characteristics of batik motifs, namely texture. There are five batik motifs used, namely inland solo batik, semarang coastal batik, sidhomukti batik, parangklithik batik, and sidhodrajat batik. Initially preprocessing is done by cropping and grayscalling. Of the five image motifs, a cropping process is carried out for each motif. The next step is feature extraction. The features of GLCM were selected in this study. From the features contained in the GLCM, in this study four features were chosen, namely contrast, energy, correlation, and homogeneity. The final step is the selection or selection of features. The result of the feature selection of the four features carried out feature extraction are energy and homogeneity.

Determination of SVM-RBF Kernel Space Parameter to Optimize Accuracy Value of Indonesian Batik Images Classification

Abstract: Image retrieval using Support Vector Machine (SVM) classification verydepends on kernel function and parameter. Kernel function used by dot productsubstitution from old dimension feature to new dimension depends on imagedataset condition. In this research, parameter of Gaussian /Radial BasisFunction (RBF) kernel function is optimized using multi class non-linear SVMmethod and implemented to training and test datasets of traditional Indonesian batik images. The batik images dataset is limited to four geometric motifs textures,which are ceplok/ceplokan, kawung, nitikand parang/lerang. Discrete WaveletTransform level 3 daubechies 2 is used to result feature dataset of traditionalbatik images dataset of four classesgeometric motifs textures. The batikimages are used for training and test dataset in SVM-RBF kernel parameteroptimation to maximize accuracy value in non-linear multi-class classification.Cross Validation and Grid-search methods are used to analyze and evaluateSVM-RBF kernel parameter optimation. Confusion matrix measurement method isused to result accuracy value in every evaluationconducted in every combination of cost function/C and gamma/γ as SVM-RBF kernel parameter. Maximumaccuracy parameter value is C = 27 and γ = 2-15 achieved by 10 times evaluation wit different testdataset for each evaluation. Maximum accuracy value is 0.77 to 0.86.

Modified Convolutional Neural Network Architecture for Batik Motif Image Classification

Batik is one of the cultural heritages of Indonesia that have many different motifs in each region as well as in its usage. However, the Indonesians sometimes not knowing the batik motif that they’re wearing every day, and sometimes they have a batik image without knowing batik information contained in their batik image. With the growing number of images of batik and batik motifs, a classification method that can classify various motifs of batik is required to automatically detect the motif from the batik image. Image processing using the Deep Learning especially for image classification is widely used recently because it has good results. The most popular method in deep learning is Convolutional Neural Network (CNN) which has been proved robust in natural images. This study offers a batik motif image classification system using CNN method with new network architecture developed by combining GoogLeNet and Residual Networks named IncRes. IncRes merges the Inception Module with Residual Network structure. With the 70.84% accuracy, the system can be used to classify the batik image motif accurately.

Semantic Madurese Batik Search with Cultural Computing of Symbolic Impression Extraction and Analytical Aggregation of Color,Shape and Area Features

Lack of information media about Madurese batik Causes low awareness of younger generation to maintain the production of Madurese batik. Actually, Madurese Batik also has a high philosophy, which the motif and colour reflect the character of the Madurese. Madurese Batik has useful motif as a mean of traditional communication in the form of certain cultural symbols. We collected images of Madurese Batik by identifying the impression of Madurese Batik motif taken from several literature books of Madurese Batik and also the results of observation of experts or craftsmen who understand about Madurese Batik. This research proposed a new approach to create on application which can identify Madurese Batik impression by using 3D-CVQ feature extraction methods to extract color features, and used Hu Moment Invariant for feature feature extraction. Application searching of Madurese Batik image has two ways of searching, those are based on the image input Madurese Batik and based on the input of impression Madurese batik. We use 202 madurese batik motifs and use search techniques based on colors, shapes and aggregations (color and shape combinations). Â Performance results using based on image queries used: (1) based on color, the average precision 90%, (2) based on shape, the average precision 85%, (3) based on aggregation, the average precision 80%, the conclusion is the color as the best feature in image query. While the performance results using based on the impression query are: Â (1) based on color, the average value of true 6.7, total score 40.3, (2) based on shape, the average value of true 4.1, total score 24.1, and (3) based on the aggregation, the average value of true 2.5, the total score is 13.8, the conclusion is the color as the best feature in impression query.

An Integrated Color and Intensity Co-Occurrence Matrix for Batik Image Retrieval

An Integrated Color and Intensity Co-Occurrence Matrix for Batik Image Retrieval

Deteksi Batik Parang Menggunakan Fitur Co-Occurence Matrix Dan Geometric Moment Invariant Dengan Klasifikasi KNN

Batik motifs are the base or the blueprint of batik patterns which serve as the core of the batik image design, and therefore the meaning of a sign, symbol or logo in a batik work can be revealed through its motifs. Visual identification requires visual skills and knowledge in classifying patterns formed in a batik image. Lack of media providing information on batik motifs makes the public unable to have sufficient information about batik motifs. Looking at this phenomenon, this study is conducted in order to perform visual identification using a computer that can assist and facilitate in identifying the types of batik. The methods used for batik image recognition are the Co-occurrence Matrix method to provide extraction of batik texture features, and the Geometric Moment Invariant method, while K Nearest Neighbor is used to classify batik images. The results on the accuracy values obtained reveal that the of 80%, compared to the accuracy value result using the Co-occurrence Matrix method that is 70%.