Kemal Özkan

Wheat grain classification by using dense SIFT features with SVM classifier

We put an automated system to classify the wheat grains with a high accuracy rate.We used the performance of DSIFT evaluated by SVM classifier.The proposed method provides an overall 88.33% accuracy rate. The demand for identification of cereal products with computer vision based applications has grown significantly over the last decade due to economic developments and reducing the labor force. With this regard, we have proposed an automated system that is capable to classify the wheat grains with the high accuracy rate. For this purpose, the performance of Dense Scale Invariant Features (DSIFT) is evaluated by concentrating on Support Vector Machine (SVM) classifier. First of all, the concept of k-means clustering is operated on DSIFT features and then images are represented with histograms of features by constituting the Bag of Words (BoW) of the visual words. By conducting an experimental study on a special dataset, we can make a commitment that the proposed method provides the satisfactory results by achieving an overall 88.33% accuracy rate.

A new classification scheme of plastic wastes based upon recycling labels

Since recycling of materials is widely assumed to be environmentally and economically beneficial, reliable sorting and processing of waste packaging materials such as plastics is very important for recycling with high efficiency. An automated system that can quickly categorize these materials is certainly needed for obtaining maximum classification while maintaining high throughput. In this paper, first of all, the photographs of the plastic bottles have been taken and several preprocessing steps were carried out. The first preprocessing step is to extract the plastic area of a bottle from the background. Then, the morphological image operations are implemented. These operations are edge detection, noise removal, hole removing, image enhancement, and image segmentation. These morphological operations can be generally defined in terms of the combinations of erosion and dilation. The effect of bottle color as well as label are eliminated using these operations. Secondly, the pixel-wise intensity values of the plastic bottle images have been used together with the most popular subspace and statistical feature extraction methods to construct the feature vectors in this study. Only three types of plastics are considered due to higher existence ratio of them than the other plastic types in the world. The decision mechanism consists of five different feature extraction methods including as Principal Component Analysis (PCA), Kernel PCA (KPCA), Fishers Linear Discriminant Analysis (FLDA), Singular Value Decomposition (SVD) and Laplacian Eigenmaps (LEMAP) and uses a simple experimental setup with a camera and homogenous backlighting. Due to the giving global solution for a classification problem, Support Vector Machine (SVM) is selected to achieve the classification task and majority voting technique is used as the decision mechanism. This technique equally weights each classification result and assigns the given plastic object to the class that the most classification results agree on. The proposed classification scheme provides high accuracy rate, and also it is able to run in real-time applications. It can automatically classify the plastic bottle types with approximately 90% recognition accuracy. Besides this, the proposed methodology yields approximately 96% classification rate for the separation of PET or non-PET plastic types. It also gives 92% accuracy for the categorization of non-PET plastic types into HPDE or PP.

A robust CSS corner detector based on the turning angle curvature of image gradients

In this study, we present a new contour-based corner detection method based on the turning angle curvature computed from the contour gradients of the image. In general, curvature is computed with the pixel locations of the extracted image contours. In most contour extraction methods, the image gradient information is already computed. The proposed algorithm makes use of this available information to compute the curvature function and takes local extremums as potential corner candidates. Afterwards, the candidates are validated by a novel validation algorithm which tries to approximate the local geometric structure of the contour with an iterative least squares estimation algorithm. Thus, we not only eliminate the false detected corners; but also estimate the corner strength precisely in terms of degrees. The experiments show that the detected corners with gradient-based turning angle curvature are more durable to affine transformations according to the ACU and LE criterions.

Image denoising using common vector approach

Common vector approach (CVA) is an increasingly popular classification method in recognition problems where probability of having the dimensionality of the problem higher than the number of data items is not zero. In CVA, common component of the members of classes is separated from the discriminating difference parts and used to determine whether a given vector (a block of data) belongs to the class in question, or to find out the class it belongs to. In this study, overlapping image blocks near the current pixel to be denoised are used as input data and a class is constructed per pixel position. Denoised image block is then constructed with the sum of common vector of the class and difference vector of the centre block denoised by linear minimum mean square error estimation technique. Since the classes are formed using similar blocks, the edges are preserved while denoising the image.

Least Squares Sub-pixel Registration Refinement Using Area Sampler Model

Super-resolution applications require sub-pixel registrations of low resolution images to be almost exact due to the deterioration caused by inaccurate image registration. A linear-least-squares technique is proposed to refine sub-pixel translation parameters, which can be employed when the images are registered but just where there is not enough sub-pixel accuracy. In the technique, it is assumed that low resolution pixels are obtained by area sampling high resolution pixel field which have twice the density of their low resolution correspondents. Using this downsampling schema, a set of equations is formed. Assumed geometry and layout provide a constraint set to be used with the equation set. The sub-pixel translations are then found using least-squares-solution-with-equality-constraints. The method is shown to improve the registration accuracy.

Denoising speech signal using common vector approach

In this paper, we proposed a speech signal denoising method using common vector approach (CVA) for very noisy signals. Based on CVA, classes are constructed from windowed speech samples/vectors according to their characteristics and denoising is performed on difference vectors. Speech signal is then reconstructed using denoised patches. Size of windows and amount of overlapping are important parameters in this method, affecting the performance/noise reduction ratio. CVA results are compared against the results of Geometric Approach and Magnitude Squared Spectrum methods according to well-known performance measures. Experimental results show that the proposed common vector based method is superior to other techniques for very noisy speech signals. Method is open to enhancement with different parameters and noise estimation methods.

Prediction for the solid waste composition by use of different curve fitting models: A case study

This study presents a methodology for the prediction of solid waste composition in the urban area based on a set of limited samples. The methodology was applied by a case study for Eskişehir city in Turkey. For this purpose, Municipal Solid Waste (MSW) samples were collected for one year according to socioeconomic structure of districts. MSW samples were separated mainly into five groups of: paper-cardboard, metals, glass, plastics and food wastes as manually. The 75% of the values for each group were used as train data sets and the remains were used as test sets considering to income levels and population. It was used different curve fitting models for training of data and obtained different equations (power, exponential and polynomial) from the models. These equations were used for prediction of test sets and real values and test results were compared. Prediction accuracies were determined and interpreted according to different goodness of measurement values. It was seen that the effect of income level and population on waste composition from the degree of accuracy of this model is very important.

A novel multi-scale and multi-expert edge detection method based on common vector approach

Edge detection is most popular problem in image analysis. To develop an edge detection method that has efficient computation time, sensing to noise as minimum level and extracting meaningful edges from the image, so that many crowded edge detection algorithms have emerged in this area. The different derivative operators and possible different scales are needed in order to properly determine all meaningful edges in a processed image. In this work, we have combined the edge information obatined from each operators at different scales with the comcept of common vector apprach and obtained edge segments that connected, thin and robust to the noise.

Description of contour with meaningful points

One of the most visually descriptive features for images is the contour of the object(s). In order to describe objects with lesser number of descriptors, linear or cubic curves are fitted to the contours of the objects. The end points of these finite length curves are usually meaningful spots on the contours. In the work presented here, edges are found by the Canny edge detector, followed by Principal Component Analysis (PCA) for determining corners and inflection points. These points are classified as dominant, corner, soft corner or inflection points. Curves are fitted to the sub-contours between successive such descriptive points on the object contour.

Corner detection with bilateral filtering of freeman codes

Shape contours are one of the most widely used features in the shape detection and recognition applications. A contour can be represented by the chain code which is obtained by coding the relative directions of the elements which form that contour. Sharp transitions in a chain code of a shape contour correspond to the notches and corners that the shape has on the 2D plane. Moreover, very useful information about geometric structures and orientations of the shapes can be obtained by examining the distribution and the moments of the chain code. But chain codes may not be robust to the rotation because of the quantization process of digitizing the curves. Besides, obtaining them from real images in an efficient way is another tough problem. In this work, efficient chain codes are extracted from real images by Edge Drawing method and a corner detection algorithm based on bilateral filtering is proposed.