Search

In this paper, we propose an improvement of an automatic detection method for carotid artery calcification in dental panoramic radiographs based on local features. To reduce misdetections for the candidate region of the calcification, the proposed method is focused on the estimated shape of the calcification. Machine learning is also applied to distinguish the misdetections. A new removal method for the mandibular bone and the area below mandible is also proposed. The proposed method can reduce the misdetection of the carotid artery calcification. The experimental result shows that the improvement of the detection performance is obtained. [ABSTRACT FROM PUBLISHER]

In this paper, we propose a hue-preserving multi-scale retinex (MSR) for color images. In a color image restoration process, MSR is applied to each channel (i.e., red, green and blue) independently. Since MSR is included logarithm operation and local illumination of each channel is estimated independently, the hue of retinex output is different from the original (input) image. Hue preservation is necessary for color image processing. Distortion may occur if hue is not preserved. It is known that two operations, scaling and shifting, are hue-preserving operations in RGB color space. In the proposed method, we approximate the relationship between input pixel value and MSR output pixel value by the hue-preserving transformation form which is a combination of scaling and shifting. The efficiency of the proposed method is shown by using color checker and natural images. [ABSTRACT FROM PUBLISHER]

Histogram equalization (HE) is a simple and effective method for contrast enhancement as it can automatically define the gray-levels transformation function based on the distribution of gray-levels included in the image. HE fails to produce satisfactory results for a broad variety of low-contrast images because the HE does not use a spatial feature included in the input image. The differential gray-levels histogram which is contained edge information of the input image, were defined. Furthermore, the differential gray-levels histogram equalization (DHE) has been proposed. The DHE shows better enhancement results compared to the HE results for many kinds of images. In this paper, we propose a DHE method for color images. In the case of color images, two differential gray-level histograms can be defined. One is intensity gray-levels histogram, the other is saturation gray-levels histogram. The differential histogram for color image is defined in combination with two gray-levels histograms. The DHE method is extended to the color image processing by using the differential gray-levels histogram for color image. The proposed method has one parameter and the emphasis property of color images can be controlled by the parameter. The guideline for decision of the parameter which is agreed in a human sense is shown. [ABSTRACT FROM PUBLISHER]

While enhancing the intensity or saturation component for high-quality color enhancement, keeping the hue component unchanged is important; thus, perceptual color models such as HSI and HSV were used. Hue-Saturation-Intensity (HSI) is a public color model, and many color applications are commonly based on this model. However, the transformation form HSI model to RGB model usually generates the gamut problem after processing intensity and saturation in the HSI model. Moreover, the saturation component is always increased or decreased following the change of intensity component no matter what the attainable saturation range is. In this paper, we propose accurate formulas for the color transformation between RGB and the proposed HSI color model which is named the improved HSI (I-HSI) color model. Furthermore, we show a simple enhancement method of color images based on the gamma transformation. In experiments, we show the validity of the I-HSI color model under the comparison with the conventional HSI color model. [ABSTRACT FROM PUBLISHER]

This study aimed to realize and compare the effectiveness of cortical and trabecular bone measures in a computer-aided system based on support vector machine (SVM) for identifying postmenopausal women with low BMD or osteoporosis. Dental panoramic radiographs of 69 postmenopausal women, as well as bone mineral density (BMD) assessments at the lumbar spine and the femoral neck were used. Average width and variance of continuous measurements of mandibular cortical bone and distribution of average length and angle (direction) of trabecular bone segments on panoramic radiographs were measured by computer-aided systems and used as inputs. The accuracy of the cortical measures using average width and variance was 87% and of the trabecular measures using average length and angle was 65% with RBF kernel-SVM method for diagnosing women with low BMD at the lumbar spine. Likewise, the accuracy of combined cortical and trabecular bone measures was 88%. Our results suggest that the cortical bone measurement is more appropriate than the trabecular bone measurement for triage screening of osteoporosis. [ABSTRACT FROM PUBLISHER]

In many techniques of color image enhancement, processing intensity and saturation keeping hue unaltered is the transformation of the image data from RGB color space to other color space such HSI, YIQ, HSV, etc. Transforming from one space to another and processing in these spaces usually generate gamut problem. In this paper, we have proposed a new enhancement scheme that enables one to apply a class of grey scale image enhancement methods to color images with free from gamut problem since color images are processed within RGB color space. The proposed processing framework guarantees the preserving hue while increasing saturation of enhancement results. The grey scale histogram equalization is applied to our generic framework in order to realize 3-D histogram equalization. [ABSTRACT FROM PUBLISHER]

Hue (H), saturation (S) and intensity (I) are the attributes of color. Therefore, a lot of color image enhancement techniques are performed in HSI color space. In this paper, a new color image contrast enhancement method is proposed in HSI color space. Histogram equalization (HE) is a popular technique for contrast enhancement of images. It is the most commonly used method due to its simplicity and comparatively better performance on almost all types of images. However, HE shows unnatural results for images with large background. In order to improve this drawback of HE, HE with variable enhancement degree (HE-VED) is introduced. The enhancement degree of HE-VED is controlled by one parameter. Then, HE-VED is applied to saturation and intensity histograms separately. In this paper, we aimed mainly at natural color images include human faces. In the kind of image, it is necessary to describe skin color accurately. Thus, we adjust a parameter of HE-VED, in order to restore the skin color of human faces. [ABSTRACT FROM PUBLISHER]

Iris recognition is one of the most reliable biometric technologies. Iris feature extraction is a key issue in iris recognition. This paper proposes a novel method to extract the features of space domain from iris image, which uses gray-scale morphological filtering. It is well known that the skeleton which shows the features of images is extracted from binary images by morphological filtering. The skeleton of gray scale images can be also extracted by gray-scale morphological filtering. In order to extract the features of the iris, we apply the gray-scale morphological filtering to the iris image and obtain its skeleton. The binary skeleton which is regarded as the iris code is obtained by threshold processing. The Hamming distance was employed for classification of iris codes. In the proposed method, the Hamming distance of intro class and inter class are separated completely. [ABSTRACT FROM PUBLISHER]

Color bit-length (i.e., resolution of signal amplitude) is an important attribute to image quality. The bit-length is decided by the quantization of image capture devices. The precision in various image capture devices limits the color bit-length and introduces loss in visual quality. Expanding the bit-length is important image enhancement issue. For example, the bit-length expansion technique is necessity for the high-quality display such as the liquid crystal display (LCD) and the plasma display. Since, these displays have more the 10-bit resolution for each color component. However, in general, color image signals are defined by 8bit resolution for each component. Moreover, the bit-length expansion technique is also necessary for low bit-length captured images. If we expand bit-length of these images by using most bit-length expanding algorithms, pseudo contouring effect is observed in smooth gradient area. The bit-length expansion process and inverse quantization process are equivalent. Inverse quantization is able to perform by suitable filtering. In this paper, the bit-length expansion method using a nonlinear filter with adaptive window size is proposed. We show the excellent bit-length expanded results are obtained by the proposed method. [ABSTRACT FROM PUBLISHER]

Histogram equalization (HE) is a simple and effective method for contrast enhancement as it can automatically define the gray-levels transformation function based on the distribution of gray-levels included in the image. HE fails to produce satisfactory results for a broad variety of low-contrast images because the HE does not use a spatial feature included in the input image. This paper proposes a novel contrast enhancement method using not only the conventional histogram but also the differential gray-levels histogram of the input image. The differential gray-levels histogram contains edge information of the input image. Edge information is one of the important spatial features of the image. We can identify the regions where are desired to be emphasized by using both the conventional histogram and the differential gray-levels histogram. Thus, for example, the proposed method can emphasize the objects which are buried in shadow or saturation regions efficiently. [ABSTRACT FROM PUBLISHER]