• Journal of the Institute of Convergence Signal Processing
• /
• v.10 no.4
• /
• pp.239-244
• /
• 2009

Image contrast enhancement has an important role in image processing applications. Conventional contrast enhancement techniques, histogram stretching and histogram equalization, and many methods based on histogram equalization often fail to produce satisfactory results for broad variety of low-contrast images. So, this paper proposes a new image contrast enhancement method based on the clustering method. The number of cluster of histogram is found by analysing the histogram of original image. The histogram components is classified using K-means algorithm. And then these histogram components are performed histogram stretching and histogram equalization selectively by comparing cluster range with pixel rate of cluster. From the expremental results, the proposed method was more effective than conventional contrast enhancement techniques.

• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.314-321
• /
• 2022

Depth information used in SLAM and visual odometry is essential in robotics. Depth information often obtained from sensors or learned by networks. While learning-based methods have gained popularity, they are mostly limited to RGB images. However, the limitation of RGB images occurs in visually derailed environments. Thermal cameras are in the spotlight as a way to solve these problems. Unlike RGB images, thermal images reliably perceive the environment regardless of the illumination variance but show lacking contrast and texture. This low contrast in the thermal image prohibits an algorithm from effectively learning the underlying scene details. To tackle these challenges, we propose multi-channel remapping for contrast. Our method allows a learning-based depth prediction model to have an accurate depth prediction even in low light conditions. We validate the feasibility and show that our multi-channel remapping method outperforms the existing methods both visually and quantitatively over our dataset.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.4
• /
• pp.707-714
• /
• 2019

Recently, as the sensor network technologies and camera technologies develops, there are increasing needs by combining two technologies to effectively observe or monitor the areas that are difficult for people to access by using the visual sensor network. Since the applications using visual sensors take pictures of the outdoor areas, the images may not be well contrasted due to cloudy weather or low-light time periods such as a sunset. In this paper, we first model the color characteristics according to illumination using the characteristics of visual sensors that continuously capture the same area. Using this model, a new method for improving low contrast images in real time is proposed. In order to make the model, the regions of interest consisting of the same color are set up and the changes of color according to the brightness of images are measured. The gamma function is used to model color characteristics using the measured data. It is shown by experimental results that the proposed method improves the contrast of an image by adjusting the color components of the low contrast image simply and accurately.

• Imaging Science in Dentistry
• /
• v.37 no.3
• /
• pp.157-163
• /
• 2007

Purpose: To evaluate the characteristics of (widely used) cone beam computed tomography (CBCT) images. Materials and Methods: Images were obtained with CT performance phantoms (The American Association of Physicists in Medicine; AAPM). CT phantom as the destination by using PSR $9000N^{TM}$ dental CT system (Asahi Roentgen Ind. Co., Ltd., Japan) and i-CAT CBCT (Imaging Science International Inc., USA) that have different kinds of detectors and field of view, and compared these images with the CT number for linear attenuation, contrast resolution, and spatial resolution. Results: CT number of both PSR $9000N^{TM}$ dental CT system and i-CAT CBCT did not conform to the base value of CT performance phantom. The contrast of i-CAT CBCT is higher than that of PSR $9000N^{TM}$ dental CT system. Both contrasts were increased according to thickness of cross section. Spatial resolution and shapes of reappearance was possible up to 0.6 mm in PSR $9000N^{TM}$ dental CT system and up to 1.0 mm in i-CAT CBCT. Low contrast resolution in region of low contrast sensitivity revealed low level at PSR $9000N^{TM}$ dental CT system and i-CAT CBCT. Conclusion: CBCT images revealed higher spatial resolution, however, contrast resolution in region of low contrast sensitivity was the inferiority of image characteristics.

• Journal of radiological science and technology
• /
• v.44 no.4
• /
• pp.295-300
• /
• 2021

This study aims to present new chest AP examination exposure conditions through a study on the effect on image quality and patient dose by applying high tube voltage and scatter ray post-processing software during chest AP examination in digital radiography equipment. This study was used a human body phantom and in the chest AP position, the dosimeter was placed horizontally at the thoracic spine 6. The experiment was conducted by dividing into a low tube voltage (70 kVp, 400 mA, 3.2 mAs) group and a high tube voltage (100 kVp, 400 mA, 1.2 mAs) group. The collimation size (14″× 17″) and the source to image receptor distance(110 cm) were same applied to both groups. Radiation dose was presented to dose area product and entrance surface dose. Image quality was compared and analyzed by comparing the difference between the signal-to-noise ratio and the contrast-to-noise ratio of the image according to the application of the scatter ray post-processing software under each condition. The average value of the entrance surface dose in the low and high tube voltage conditions was 93.04±0.45 µGy and 94.25±1.51 µGy, which was slightly higher in the high tube voltage condition, but the dose area product was 0.97±0.04 µGy and 0.93±0.01 µGy. There was a statistically significant difference in the group mean value(p<0.01). In terms of image quality, the values of the signal-to-noise ratio and the contrast noise ratio were higher in the high tube voltage than in the low tube voltage, and decreased when the scattering line post-processing function was used, but the contrast resolution was improved. If there is a scatter ray post-processing function during chest AP examination, it is helpful to actively utilize it to improve the image quality. However, when this function is not available, I thought that applying a higher tube voltage state than a low tube voltage state will help to realize images with a large amount of information without changing the dose.

• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.585-589
• /
• 2018

Consumer demand for high quality image/video services led to growing trend in image quality enhancement study. Therefore, recent years was a period of substantial progress in this research field. Through careful observation of the image quality after processing by image enhancement algorithms, we perceived that the dark region in the image usually suffered loss of contrast to a certain extent. In this paper, the low-light stretch preprocessing algorithm is, hence, proposed to resolve the aforementioned issue. The proposed approach is evaluated qualitatively and quantitatively against the well-known histogram equalization and Photoshop curve adjustment. The evaluation results validate the efficiency and superiority of the low-light stretch over the benchmarking methods. In addition, we also propose the 255MHz-capable hardware implementation to ease the process of incorporating low-light stretch into real-time imaging systems, such as aerial surveillance and monitoring with drones and driving aiding systems.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.4
• /
• pp.859-864
• /
• 2018

This paper is about image improvement - we used the contrast ratio and the outline emphasis method after synthesizing two low quality images utilized by several low definition cameras. Two raspberry cameras were used to capture each image, and then we synthesized images with MATLAB program. After applying the mean computation (alignment, geometry, and harmony) to synthesized image, we extracted the cross-space. In the experiment of this study, we identified and compared the improvement consequences of extracted, synthesized image after applying outline emphasis(unsharpmask filter, highboost filter) and increasing contrast ratio (histogram uniformity, histogram stretching) to the original images.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.11
• /
• pp.919-927
• /
• 2013

In this paper, we present a perception-based tone mapping technique using histogram modification for displaying high dynamic range image. HDR (high dynamic range) tone mapping algorithms are used to display HDR image on LDR (low dynamic rnage) devices. Although perception-based tone mapping methods provides better performance, it dose not always produce good results for a wide variety of images. The proposed method reduces dynamic range by using the perception-based tone mapping function and histogram modification. A derivative of perception-based tone mapping function is used as constraint function of histogram and additional compensation process is performed. This method not only improves contrast by adopting different constraints on each pixel value, but also preserves more visual details. In order to prevent over enhancement, histogram modification technique is applied. Furthermore, it can control the rate of image contrast using control parameters. Subjective and objective evaluations show that proposed algorithm is better than existing algorithms.

• Journal of Biomedical Engineering Research
• /
• v.11 no.1
• /
• pp.31-38
• /
• 1990

Image correction of the fluorescein angiogram with the low contrast and geometrically distorted is studied. The procedure is divided into two steps : A template matching step and a geometrical transformation step. Based on the sequential similiarity detection algorithm, more Improved matching results are obtained with edge enhanced image. For the reference points and the corresponding matchimg points, the geometrical transformationss by the use of the average value of the X, Y translational shifts and a pair of these points, respectively are described. Then the corrected images are obtained using bilinear interpolation. It is proven that the usefullness of this study for the image correction of the ocular fundus fluoresceln angiogram with low contrast and geometrically distorted mainly due to the eye movements.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.1
• /
• pp.64-69
• /
• 2021

In this paper, a method for improving the defect classification performance in low contrast, ununiformity and featureless steel plate surfaces has been studied based on deep convolution neural network and transfer-learning neural network. The steel plate surface images have low contrast, ununiformity, and featureless, so that the contrast between defect and defect-free regions are not discriminated. These characteristics make it difficult to extract the feature of the surface defect image. A classifier based on a deep convolution neural network is constructed to extract features automatically for effective classification of images with these characteristics. As results of the experiment, AlexNet-based transfer-learning classifier showed excellent classification performance of 99.43% with less than 160 seconds of training time. The proposed classification system showed excellent classification performance for low contrast, ununiformity, and featureless surface images.