Label noise detection has been widely studied in Machine Learning because of its importance improving training data quality. Satisfactory achieved by adopting ensembles classifiers. In this approach, an instance is assigned as mislabeled if a high proportion members the pool misclassifies it. Previous authors have empirically evaluated approach; nevertheless, they mostly assumed that label gene...

One of the key issues in removing random-valued impulse noise from digital images using switching filters is the impulse noise detection. Impulse noise is a random, spiked variation in the brightness of the image. In this paper, a new impulse noise detection algorithm is presented that is based on Noise ratio Estimation and a combination of K-means clustering and Non-Local Means based filter (N...

The method of removing the existing Impulse noise was to find threshold and apply median filter remove noise. In this paper, we try reference values in neural networks. order noise, used a non-local consider not only information region but also entire region. We then utilized Yolo's grid cell structure make stronger predictions considering various sizes different areas. Accordingly, qualitative...

Five new theorems and a stochastic learning algorithm show that noise can benefit threshold neural signal detection by reducing the probability of detection error. The first theorem gives a necessary and sufficient condition for such a noise benefit when a threshold neuron performs discrete binary signal detection in the presence of additive scale-family noise. The theorem allows the user to fi...

Noise Suppression from images is one of the most important concerns in digital image processing. Impulsive noise is one such noise, which may corrupt images during their acquisition or transmission or storage etc. A variety of techniques are reported to remove this type of noise. It is observed that techniques which follow the two stage process of detection of noise and filtering of noisy pixel...

We discuss the signal detection through nonlinear threshold systems. The detection performance is assessed by the probability of error Per . We establish that: (1) when the signal is complete suprathreshold, noise always degrades the signal detection both in the single threshold system and in the parallel array of threshold devices. (2) When the signal is a little subthreshold, noise degrades s...

Edge detection is used widely from consumer applications to military and medical image analysis. One of the challenges in edge detection is getting the best trade-off between reliable detection and noise robustness. Because of that it is important to develop reliable edge detection algorithm which can adapt to different noise levels keeping false detections at minimum. In this paper we propose ...