No abstract

Abstract-Leather craft products, such as belt, gloves, shoes, bag, and wallet are mainly originated from cow, crocodile, lizard, goat, sheep, buffalo, and stingray skin. Before the skins are used as leather craft materials, they go through a tanning process. With the rapid development of leather craft industry, an automation system for leather tanning factories is important to achieve large scale production in order to meet the demand of leather craft materials. The challenges in automatic leather grading system based on type and quality of leather are the skin color and texture after tanning process will have a large variety within the same skin category and have high similarity with the other skin categories. Furthermore, skin from different part of animal body may have different color and texture. Therefore, a leather classification method on tanning leather image is proposed. The method uses pre-trained deep convolution neural network (CNN) to extract rich features from tanning leather image and Support Vector Machine (SVM) to classify the features into several types of leather. Performance evaluation shows that the proposed method can classify various types of leather with good accuracy and superior to other state-of-the-art leather classification method in terms of accuracy and computational time.

sebagai kerangka, penopang tubuh manusia dan tempat melekatnya otot, sehingga tubuh dapat bergerak maksimal. Tidak hanya itu, beberapa bagian tulang juga memiliki fungsi untuk melindungi organ lain didalam tubuh. Seperti tulang tengkorak yang berfungsi melindungi otak dari berbagai macam benturan dari luar, susunan tulang rusuk yang berfungsi untuk melindungi paru-paru dan sebagainya. Itulah yang menjadikan fungsi tulang menjadi sangat vital apabila terjadi kerusakan pada tulang itu sendiri.Badan kesehatan dunia (WHO) mencatat tahun 2007 terdapat lebih dari delapan juta orang meninggal dikarenakan insiden kecelakaan dan sekitar 2 juta orang mengalami kecacatan fisik. Salah satu insiden kecelakaan yang memiliki angka kejadian yang cukup tinggi yakni insiden fraktur ekstremitas bawah yakni sekitar 46,2% dari insiden kecelakaan yang terjadi. Berdasarkan hasil Riset Kesehatan Dasar (RISKESDAS) oleh Badan Penelitian dan Pengembangan Depkes RI tahun 2007 di Indonesia terjadi kasus fraktur yang disebabkan oleh cedera antara lain karena jatuh, kecelakaan lalu lintas dan trauma

This research work proposes a novel method to improve quality of animal leather images using digital image processing approach. In this work, piecewise linear contrast stretch based on unsharp masking algorithm is employed for image enhancement. The proposed method minimizes contrast problem. Experiments had been done on four categories of animal leather images namely crocodile leather, monitor lizard leather, cow leather and goat leather. The proposed method was then compared with other piecewise linear transforms based image enhancement techniques including intensity level slicing, bit plane slicing and contrast stretching methods. PSNR, MSE and SSIM values were obtained by using our proposed method and our proposed method produced better result. The values of PSNR when using piecewise linear contrast stretch unsharp masking (PLCSUS) respectively for crocodile leather, monitor lizard leather, cow leather and goat leather are 30.06 dB, 18.97 dB, 20.66 dB and 14.73 dB. This value is higher when compared to using other methods on the same image. Experiments show that our proposed method is better compared to conventional methods with respect to special characteristics of animal leather to be used as raw materials of artworks.

No abstract