To recognize the batik pattern automatically, we implement a batik classification method using kNN and ANN. #Batik mega mendung vector definition windowsThis algorithm is multiwindow and multiscale extended center symmetric local binary patterns (MU2ECS-LBP) which uses several windows such as the size of 6圆, 9x9, 12x12, and 15x15 or a combination between windows. The batik‘s pattern of changing this dilemma at the same time needs a feature extraction algorithm that is reliable in supporting image classification. Batik’s pattern automatic classification still requires some improvement especially in regards to invariant with scale and rotation. Types of batik motifs collected through several sources such as batik magazines, the internet or directly using a digital camera. The future work will be done by carrying out more data training to increase performance, obtaining more pattern designs, and developing an application based on a high-performance model.īatik in Indonesia has various types of patterns, which are arranged repeatedly to illustrate the basic motifs of cloth as a whole. The test accuracy rates of pattern design recognition for MobileNets, Inception-v3, and Inception-v4 are 94.19, 92.08, and 91.81%, respectively. The results of the test show that MobileNets outperforms Inception-v3 and Inception-v4. The data were trained and tested based on 10-fold cross-validation approach. For each pattern, there were 180 images segmented and there were 1,800 images in total in the dataset. The research collected images of real silk fabrics containing 10 pattern designs. In recognizing pattern design, three deep learning models were experimented: Inception-v3, Inception-v4, and MobileNets. The research aims at recognizing woven fabric pattern designs of traditional fabrics called Phasin in Loei province, Thailand based on deep learning methods. Pattern recognition methods can help classify these pattern designs without having to find an expert. Hand-woven fabric pattern designs commonly represent the tradition and culture of local communities. The accuracy score shows that the model trained with the suggestion based picture perform better than the one trained with the random picture. One type is a freely taken image, the other two were taken based on the experts suggestion. The two CNN models, inceptionV3 and mobilenetV2 were trained on three types of image. We realize that this problem is go beyond the recognition of fine grained image problem, it is a hard to identify image problem because even the batik experts is having a hard time identifying batik and its imitation if only based on its picture. Tulis and cap are genuine batik, and the other three are an imitation. The classes are tulis, cap, print warna, print malam, cabut warna. We try to compare two popular CNN model to classify batik products into five classes. Batik is an Indonesian heritage of process in making traditional textile product that is now endangered by the existence of imitation products. Span id="docs-internal-guid-25a2977b-7fff-96bd-b93a-19bd55e68ea7"> In this research we try to solve the recognition problem in differentiating between batik and its imitation.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |