Yazar "Talu M.F." seçeneğine göre listele
Listeleniyor 1 - 7 / 7
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe AUTOMATIC MEASUREMENT OF SHRINKAGE RATE IN DENIM FABRICS AFTER WASHING(Chamber of Textile Engineers, 2021) Talu M.F.In a large-scale garment facility, an average of 300–350 fabric rolls (150 meters each) is washed daily. Measuring the changes in fabric sizes with the washing process, transferring them to the fabric follow-up form, and saving the follow-up forms to the system at the end of the day are performed manually. In these processes where 6–7 personnel are involved, different quality control errors occur due to incorrect measurement or writing. In this study, a new system based on a computer vision system that can automatically calculate the shrinkage occurring in the fabric during the washing process and transfer it to the system is proposed. The proposed system consists of data collection and processing stages. In data collection, colored fabric images obtained with a CCD camera before and after washing are recorded with the help of a prepared cabinet. The processing phase includes the steps of removing the lens effect from the images, filtering, line detection by Hough transform, and computing the draw. As a result of experiments on six different fabric types, it has been observed that there is a %0.5–0.33 difference (within tolerance) between manual measurement of the shrinkage value and measured using the proposed system. © 2021. All Rights Reserved.Öğe Ayni Şartlar Altinda Farkli Üretici Çekişmeli A?larin Karşilaştirilmasi(Institute of Electrical and Electronics Engineers Inc., 2019) Altun S.; Talu M.F.As the first successful general purpose way of generating new data, GANs have shown great potential for a wide range of practical applications (including those in the fields of art, fashion, medicine and finance). It is one of the most popular research topics of recent times. GANs are the new class of exciting machine learning model that leads to applications that bring to mind their ability to produce synthetic but realistic looking data. Generative Adversarial Networks are composed of two neural networks that work in opposite directions. In this paper, it is aimed to examine the same initial situation, same dataset, same number of iterations, parts of the same size in order to compare Generative Adversarial Networks. This paper Generative Adversarial Network (GAN), Deconvolusional Generative Adversarial Network (DCGAN), Semi-Supervised Generative Adversarial Network (SGAN/SeGAN) Conditional Generative Adversarial Network (CoGAN / CGAN) were used. These methods were calculated on the performance of MNIST dataset. The results are presented both numerically and visually. © 2019 IEEE.Öğe Hybrid lossless compression method for binary images(Istanbul University, 2011) Talu M.F.; Türkoglu I.In this paper, we propose a lossless compression scheme for binary images which consists of a novel encoding algorithm which uses a new edge tracking algorithm. The proposed compression scheme has two sub-stages: (i) encoding binary image data using the proposed encoding method (ii) compression the encoded image data using any well-known image compression method such as Huffman, Run-Length or Lempel-Ziv-Welch (LZW). The proposed encoding method contains two subsequent processes: (i) determining the starting points of independent objects (ii) obtaining their edge points and geometrical shapes information. Experimental results show that using the proposed encoding method together with any traditional compressing method improves the compression performance. Computed mathematical results related to compression performance are represented comparatively in a tabular format.Öğe Interactive segmentatition implementation(Institute of Electrical and Electronics Engineers Inc., 2015) Alasu S.; Talu M.F.This paper includes a geodesic distance based interactive segmentation algorithm's Matlab implementation. In the Matlap implementation, a graphic interface by which user creates foreground and background scribbles over the image has been designed. The first step of the algorithm is based on the modelling of the color values on the scribbles and the calculation of foreground/background probabilities of all pixels in the image. In the second step, the calculated probabilities values are accepted as weight values and the segmentation process has been implemented more precision by using geodesic distance method. It can be show that to able to produce precise segmentation results in real-time, the algorithm can be used especially in medical image segmentation applications. © 2015 IEEE.Öğe A novel texture classification method based on Hessian matrix and principal curvatures(IEEE Computer Society, 2014) Alpaslan N.; Hanbay K.; Hanbay D.; Talu M.F.In this study, in order to obtain similar effect with conventional gradient operation and extract more robust feature for texture, we use the principal curvature informations instead of the gradient calculation. Through this methods, sharp and important informations about the texture images were obtained by analyzing images of the second order. Considering the classification results obtained, it is shown that the proposed method improve the performance of original CoHOG and HOG feature extraction methods. As a result of experiments on datasets with different characteristics, it is seen that, the proposed method has higher classification performance. © 2014 IEEE.Öğe Segmentation of color texture images with artificial bee colony algorithm and wavelet transform(2012) Hanbay K.; Talu M.F.; Karci A.Segmentation is an important application in the analysis of gray level and color images numerically. The task of image segmentation is to separate a given image into different regions having homogenous properties. Although the most basic segmentation is thresholding, this method has been insufficient in time. In this paper, the segmentation of color texture images is carried out with the approach of wavelet transform and artificial bee colony algorithm. Through this approach, the segmentation of typical natural scenes, including no uniform statistical color and texture characteristics is achieved. The superior and weak points of the developed method are evaluated. © 2012 IEEE.Öğe Web based image processing application: Rating diabetes intensity(Institute of Electrical and Electronics Engineers Inc., 2017) Gündüzalp V.; Talu M.F.; Gül S.; Zayman E.; Gül M.In this study, it is A web-based image processing software which has been introduced to process Immunohistochemical images obtaining in experimentally induced diabetic rats and rank the severity of diabetes between the groups. With the software, specialist physicians can upload Images obtaining in rat groups to the system via web on own account, obtain average color intensity and intensity graphs of groups after Determining the basic colors to be evaluated. The software eliminating the subjective evaluation contains mainly three phases in this study, Evaluation of each image content according to basic axes(Three-dimensional projection), Clustering of colors (Expectation maximization method) and Color-axis determination (Calculation of eigenvectors). As a result of, it can be considered that positive results obtained could stimulate Researchers to generalize of the proposed method. © 2017 IEEE.
