Median filter

About: Median filter is a research topic. Over the lifetime, 12479 publications have been published within this topic receiving 178253 citations.

A novel microaneurysms detection approach based on convolutional neural networks with reinforcement sample learning algorithm

Abstract: Microaneurysms (MAs) are known as early signs of diabetic-retinopathy which are called red lesions in color fundus images. Detection of MAs in fundus images needs highly skilled physicians or eye angiography. Eye angiography is an invasive and expensive procedure. Therefore, an automatic detection system to identify the MAs locations in fundus images is in demand. In this paper, we proposed a system to detect the MAs in colored fundus images. The proposed method composed of three stages. In the first stage, a series of pre-processing steps are used to make the input images more convenient for MAs detection. To this end, green channel decomposition, Gaussian filtering, median filtering, back ground determination, and subtraction operations are applied to input colored fundus images. After pre-processing, a candidate MAs extraction procedure is applied to detect potential regions. A five-stepped procedure is adopted to get the potential MA locations. Finally, deep convolutional neural network (DCNN) with reinforcement sample learning strategy is used to train the proposed system. The DCNN is trained with color image patches which are collected from ground-truth MA locations and non-MA locations. We conducted extensive experiments on ROC dataset to evaluate of our proposal. The results are encouraging.

Method and apparatus for cancelling common mode noise occurring in communications channels

Abstract: In order to overcome problems when using an adaptive filter for cancellation of common-mode noise in digital subscriber loops, caused by a portion of the differential signal being converted to common mode, which degrades the performance of the filter, a noise cancellation technique is proposed which compensates for this cross-coupled signal energy. In particular, a digital noise detector is used to detect one or more noisy frequency bands of the common mode signal and pass only the digitized common mode signal in those detected frequency bands through the adaptive filter to produce a digital common mode noise estimate signal. A control unit adjusts coefficients of the adaptive filter to reduce correlation between the differential signal and common mode signal. It is also proposed to compensate for the effects of stray capacitive coupling across the usual hybrid device by including an equivalent capacitive component in a common mode noise estimation circuit.

Spatio-temporal video noise reduction system

Abstract: A method and system for digital video noise reduction which includes a picture analyser (103) for analysing pictures in a video sequence to determine the amount of moving regions therein, a noise level detector (102) for estimating the noise level (N) in the video sequence, a filtering level estimator (105, 103) for determining a maximum filtering level (L) for each picture based on the amount of moving regions and the estimated noise level (N) and a spatial filter (106) and a temporal filter (107), the temporal filter being coupled to the filter level estimator for controlling the level of filtering of each picture in the sequence in accordance with the maximum filtering level.