Fitri Utaminingrum

High density impulse noise removal by Fuzzy Mean Linear Aliasing Window Kernel

Fuzzy Mean Linear Aliasing Window Kernel (FMLAWK) filter method proposed to reducing the high-density impulse noise interference and generating the smooth image performance. FMLAWK filter is a spatial filter, which combined from fuzzy method and Linear Aliasing Filter (LAF). The initial step is finding the degree of membership function (μ) value of each matrix element on the corrupted image which use the fuzzy method. Furthermore, the μ value of the corrupted image processed by LAF method which using 3×3 window. The reducing of 3×3 windows on LAF process will be obtain one pixel data based on Linear method. Our research also provides kernel algorithms. Preprocessing Kernel algorithm used for checking of each element matrix on the 3×3 window. If the matrix element contaminated by impulse noise, so the matrix element replaced with a new element data. Our simulation result shows the image filtering better and smoother quality than the comparison method.

High density impulse noise removal based on linear mean-median filter

This paper presents Linear Mean-Median (LMM) filter that used to reduce impulse noise. LMM filter is a combination between Mean and Median filter. Wherein, linear value is acquired from the linearity between mean and median value. Mean and Median filter are only applied for free-noise pixel on the 3×3 windows that has been sorted from the smallest to the largest value. The mean value is obtained from the average value of all free-noise pixels without including the median pixel position. Meanwhile, median pixel is the middle position of the pixel that has been sorted. LMM uses nine sample pixels to determine a pixel for replacement a corrupted pixel. Our filter also provides the impulse noise prediction systems that serve as a facilitator to give information about noise content. If the noise is greater than 30%, the performance of LMM filter needs to be improved by an adaptive rank order mean filters. The filtering results have shown satisfactory results in terms of the quality result and the computation time process. A good image quality can be evidenced by PSNR (Peak Signal to Noise Ratio). Our methods always have higher PSNR value than the comparison methods. In addition, the speed computation time of our method is faster than the comparison method.

Eye Movement as Navigator for Disabled Person

Eyes is one of human organs which mostly still functions properly in disabled people when other parts of the body are disabled. This research propose a new framework to recognize and detected eye movement for handling position by considering the decision of both left and right eye. The sophisticated algorithm, Haar Cascade Algorithm was used for observing the area of eyes, then thresholding image using morphology is used to obtain the focus of eyes. The Hough Circle Transform with several rules could decide the handling position of eye movement. The performance of the pro-posed algorithm could reach over 80% in all dataset.

Road detection based on the color space and cluster connecting

This paper propose a road detection, which is based on the color space and cluster connection. Generally, this method consists of two steps. The first step is road detection based on the color space. The second step is removing the fails road detection in the first step by using correlation. The correlation formula is used for calculating the similarity of each cluster image. The fails road detection will be removed, if their cluster image uncorrelated with neighbors cluster image. The simulation results show that our method has good performance which is capable significantly removing fails road detection. As well as evaluation by using precision, recall and accuracy have been presented.

Error numerical analysis for result of rainfall prediction between Tsukamoto FIS and hybrid Tsukamoto FIS with GA

Rainfall is one important aspect of everyday life, but now rainfall increasingly unpredictable. Therefore it needs to make an accurate method to predict rainfall with small error. Tsukamoto FIS and genetic algorithm is one of algorithms that can be used for prediction problems. Research using Tsukamoto FIS and hybrid Tsukamoto FIS with GA for forecasting rainfall had been done already. The prediction results generated from both methods have a diverse error value. Need an error analysis to determine which method is most optimal to predict rainfall with minimum error. Therefore, this study focuses on error numerical analysis on the result of rainfall prediction using Tsukamoto FIS and hybrid Tsukamoto FIS with GA. From the analysis, Tsukamoto FIS produce relatively small error, but this method is weak when predicting rainfall = 0 or no rain. While hybrid Tsukamoto FIS with GA produce small error for predicting rainfall = 0 or no rain. It concluded that a hybrid method Tsukamoto FIS with GA generate an error value more smaller than Tsukamoto FIS.

A laser-vision based obstacle detection and distance estimation for smart wheelchair navigation

The aim of the research is to present an approach of obstacle distance estimation and navigation for smart wheelchair. The smart wheelchair is an electric wheelchair equipped with camera and line laser to navigate and avoid an obstacle. The camera was used to capture images from the environment to sense the pathway condition. The line laser was used in combination with camera to recognize an obstacle in the pathway based on the shape of line laser image in certain angle. A blob method detection was applied on the line laser image to recognize the pattern of the detected obstacles. The line laser projector and camera were mounted in fixed-certain position to make sure a fixed relation between blobs-gaps and obstacle-to-wheelchair distance. A simple linear regression from 16 obtained data was used to represent this relation as the estimated obstacle distance. As a result, the average error between the estimation and actual distance was 1.25 cm from 7 data testing experiments. The experiments result indicates that the proposed method is able to estimate well the distance between wheelchair and obstacle. Later, the smart wheelchair needs to decide further action whether it should turn left, right or just walk straight when facing certain obstacle to avoid it.

Adaptive human tracking for smart wheelchair

People with impairment and having difficulties to walk, even impossible to move due to illness, injury, or disability need assistance tool. One assistance tool to help those people is wheelchair. With current technological developments, conventional wheelchair can be improved. Conventional wheelchair which operated by hand cannot be used by people with hand-foot impairment, as well as electric-powered wheelchair that need to be controlled with hand. For those with hand-foot impairment, conventional wheelchair can be assisted by assistant to help pushing and to maneuver. One drawback with this approach is the assistant will have limited movement and will have fatigue from pushing a wheelchair. This research try to overcome this drawback so that the wheelchair can move semi-autonomously. Proposed approach incorporates human tracking algorithm that later will be used to make the wheelchair moving independently without assistant to push from behind. This paper propose a framework that combines keypoint descriptors for human tracking: ORB, KAZE, AKAZE, BRISK, SIFT, and SURF. Each keypoint descriptors are given a score which is used to choose which descriptor is used until the minimum number of keypoints is fulfilled. If the best in the method list does not suffice, then the second best will be selected to generate keypoints, and so on. The result of the framework obtained high precision, 0.93 and 0.89 from two videos with different environments.

Rain Streaks Removal by Using Composite Method

This paper proposes rain streaks removal by combining of the smoothing methods and image enhancement. We design an efficient method for detecting and removing rain streaks in the image. The rain streaks component is obtained by reduction of the original image rain streaks with blur image, and then conducted in the quantization process. Regarding to the image quantization results, we can find a non rain streak and rain streak components. Furthermore, rain streak components are replaced by the pixels of enhancement image results that generate non-rain estimation. Finally, by implementing artefact removal from the summing of the non rain component and non rain component estimation of an image generate a rain removal method. Simulation results show the proposed method successfully eliminate the rain streaks and maintain non rain streaks.

High density impulse noise removal based on the total observation kernel element for image sequences

Several different methods for impulse noise removal in image sequences have been proposed. However, all of them are not successful in removing high density of impulse noise. Hence, this paper proposes a filtering method for reducing high density impulse noise in the image sequences. We use three windows with size 3 × 3 to obtain a new window with similar size. Three windows are taken from the next-frame, current frames and previous frames. The recursive window is applied in the current frames. The filtering process uses decision-based method. Meanwhile, a pixel for replacing the noisy pixel is calculated from a new window based on weighting method. Our experimental results show that the proposed method can not only reduce the high impulse noise in image sequences well, but also preserve more details and textures.

Onward movement detection and distance estimation of object using disparity map on stereo vision

The object tracking is used as instruction controller in wheelchair that track the movement direction of object along time. The movement direction include left, right and onward. The left and right direction can be calculated by using the changing of x-coordinate of object in every sub sequence frame. The challenge is to determine the onward moving. The onward moving cannot calculate simply by coordinate of object in 2D. The solution to detect the onward moving is by using the stereo vision camera. We proposed a method to detect the onward movement and calculate the distance of object from camera using stereo vision. The detection rate is 83.1%. The estimation of object distance from the camera is actually only 3–4 meters away. The system detect that the distance of object is 0–5 meters in front of the camera. The determination of distance estimation is appropriate with the actual distance state.