Recep Demirci

Measurement of epidermal thickness in a patient with psoriasis by computer-supported image analysis.

The aim of the present study was to measure full epidermal thickness, stratum corneum thickness, rete length, dermal papilla widening and suprapapillary epidermal thickness in psoriasis patients using a light microscope and computer-supported image analysis. The data obtained were analyzed in terms of patient age, type of psoriasis, total body surface area involvement, scalp and nail involvement, duration of psoriasis, and family history of the disease. The study was conducted on 64 patients and 57 controls whose skin biopsies were examined by light microscopy. The acquired microscopic images were transferred to a computer and measurements were made using image analysis. The skin biopsies, taken from different body areas, were examined for different parameters such as epidermal, corneal and suprapapillary epidermal thickness. The most prominent increase in thickness was detected in the palmar region. Corneal thickness was more pronounced in patients with scalp involvement than in patients without scalp involvement (t=-2.651, P=0.008). The most prominent increase in rete length was observed in the knees (median: 491 microm, t=10.117, P=0.000). The difference in rete length between patients with a positive and a negative family history was significant (t=-3.334, P=0.03), being 27% greater in psoriasis patients without a family history. The differences in dermal papilla distances among patients were very small. We conclude that microscope-supported thickness measurements provide objective results.

Fuzzy adaptive anisotropic filter for medical images

: An adaptive anisotropic diffusion filter for images is proposed in this paper. First, the gradient of an image was calculated by a novel fuzzy-rule-based gradient operator. Accordingly, the centre of gravity of a histogram of the gradient image was estimated and it was assigned as an edge threshold. In conventional anisotropic filters, the conduction coefficients have to be selected by an operator. However, in this study, the centre of gravity of the histogram was assigned as the conduction coefficient of the anisotropic filter. Consequently, an adaptive anisotropic image filter which automatically sets its conduction coefficient without user intervention was developed. The image filter achieved was tested with various medical images.

Fuzzy diffusion filter with extended neighborhood

Anisotropic diffusion filters, which are motivated from heat diffusion between mediums, have become a widely used technique in the field of image processing. In the initial proposals of anisotropic diffusion filters, 4-neighborhood values with diffusivity functions are computed independently for each spatial location because of numerical approximation. However, anisotropic diffusion filters could not be used in real-time image and video processing applications because they need diffusivity parameters, which must be specified by users in every sampling period. In this study, a fuzzy adaptive diffusion filter using extended neighborhood without diffusivity functions has been developed. The fuzzy adaptive diffusion filter does not require any parameter chosen by user and therefore they could be employed in real-time applications. In the fuzzy adaptive diffusion filter, a similarity transformation by means of relation matrix and fuzzy logic is carried out. Accordingly, the similarity image, output of transformation, is directly used as a heat diffusion coefficient in the diffusion filter. Results show that the fuzzy adaptive diffusion filter is very efficient for removing noise in image while preserving edges.

Image Clustering with Optimization Algorithms and Color Space

In image clustering, it is desired that pixels assigned in the same class must be the same or similar. In other words, the homogeneity of a cluster must be high. In gray scale image segmentation, the specified goal is achieved by increasing the number of thresholds. However, the determination of multiple thresholds is a typical issue. Moreover, the conventional thresholding algorithms could not be used in color image segmentation. In this study, a new color image clustering algorithm with multilevel thresholding has been presented and, it has been shown how to use the multilevel thresholding techniques for color image clustering. Thus, initially, threshold selection techniques such as the Otsu and Kapur methods were employed for each color channel separately. The objective functions of both approaches have been integrated with the forest optimization algorithm (FOA) and particle swarm optimization (PSO) algorithm. In the next stage, thresholds determined by optimization algorithms were used to divide color space into small cubes or prisms. Each sub-cube or prism created in the color space was evaluated as a cluster. As the volume of prisms affects the homogeneity of the clusters created, multiple thresholds were employed to reduce the sizes of the sub-cubes. The performance of the proposed method was tested with different images. It was observed that the results obtained were more efficient than conventional methods.

A novel edge detector based on light refraction law

In this paper, light refraction law based a novel edge detection algorithm was described. In the proposed method, center pixel deemed a light source. Neighbor pixels are deemed different environments refracted the light. The minimum value of ratio of these different environments refraction indices qualifies the edge knowledge of center pixels. Edges are determined rigorously in the image through this designed method. As compared with classical method, there isnpsilat very complex computing in this method.

Gradyan Anahtarlamalı Gauss Görüntü Filtresi

Gurultu goruntu isleme tekniklerinin basarisini etkileyen en onemli faktorlerden biridir. Goruntu isleme tekniklerinin basarisini arttirabilmek icin gurultunun azaltilmasi gerekmektedir. Gurultuyu azaltabilmek icin goruntulere filtreleme islemi uygulanmaktadir. Sunulan bu calismada, goruntulerdeki karisik gurultuyu giderebilmek icin filtre tasarimi yapilmistir. Goruntuye ilk olarak uyarlamali medyan filtresi uygulanmis ve goruntude tespit edilen tuz ve biber gurultusunun giderilmesi amaclanmistir. Tuz ve biber gurultusu bulunmayan piksellere ise anahtarlamali Gauss filtresi uygulanmistir. Tasarlanan anahtarlamali filtrede Gauss filtresine ait parametre kullanici mudahalesi olmadan otomatik olarak belirlenmistir. Parametrenin belirlenmesinde goruntunun gradyan bilgisi ve esik deger bilgisinden yararlanilmistir. Bu amaca yonelik olarak da MATLAB Grafik Kullanici Arayuzu (GKA) tasarlanmistir. GKA yardimiyla tasarlanan filtrenin uygulama sonuclari kameraman ve Lena goruntuleri uzerinde sunulmustur.

Similarity based anisotropic diffusion filter

Different filter methods to reduce noises occurred during image capture have been developed. One of the most effective image filters is diffusion filter. However, the major drawback of conventional diffusion filter is user-dependent. While noises are reduced with conductance coefficient arbitrarily selected, edge pixels are perceived such as noise. In this study, a novel anisotropic diffusion filter using similarity values obtained with the distance of each pixel to its neighbors has been proposed. Initially, similarity values of all image pixels are computed, and then they are used as conductance coefficients in diffusion filter. The mentioned value above is user dependent for conventional diffusion and it is constant for all pixels. On the other hand, it is made adaptive and eliminated user intervention with suggested approach. Developed method has been tested with different noise variances of images and experimental results have been compared with conventional diffusion filter.

Fuzzy logic and graph based segmentation

In this paper, a mask-based automatic segmentation algorithm for color images using fuzzy color similarity was presented. Computational cost of conventional image segmentation algorithms is high and at the same time, they are user dependent. Although the computational cost of mask-based segmentation algorithm recently introduced is low, it needs two parameters to be determined: similarity threshold and normalization factor. With proposed algorithm, pixel color similarity was calculated by means of fuzzy rule and consequently, user dependency was reduced. experimental results obtained were compared with conventional approaches.

Hybrid bilateral filter

A variety of methods for images noise reduction has been developed so far. Most of them successfully remove noise but their edge preserving capabilities are weak. Therefore bilateral image filter is helpful to deal with this problem. Nevertheless, their performances depend on spatial and photometric parameters which are chosen by user. Conventionally, the geometric weight is calculated by means of distance of neighboring pixels and the photometric weight is calculated by means of color components of neighboring pixels. The range of weights is between zero and one. In this paper, geometric weights are estimated by fuzzy metrics and photometric weights are estimated by using fuzzy rule based system which does not require any predefined parameter. Experimental results of conventional, fuzzy bilateral filter and proposed approach have been included.

Seeded region growing based detection of cells in fish blood stained with Natt-Herrick

To specify haematological parameters is a routine procedure so that state of fish health while aqua culturing could be determined. So, important information related to diagnosis and treatment can be obtained by determining them. Natt & Herricks stain solution is the most commonly method for determining haematological parameters. It is quite difficult and time-consuming to specify count of cells and to asses blood samples taken by the solution at microscope environment as a visually judgment. In this study, an automated method independent of user intervention based on seeded region growing for specifying cell related to fish blood with Natt & Herricks stain solution is developed. To evaluate of performance of proposed method, 90 images of different species of fish (rainbow trout, sea bream) prepared with Natt & Herricks stain solution by 100× zoom ratio are used. Results obtained proposed method determines cells with 97% accuracy.