Histogram equalization

About: Histogram equalization is a research topic. Over the lifetime, 5755 publications have been published within this topic receiving 89313 citations.

Image enhancement method using histogram equalization

Abstract: In an image enhancement method is disclosed using a histogram equalization for an input image expressed in a predetermined number of gray levels. While calculating the probability density function of the gray levels of the input image, for use in a histogram equalization, the number of occurrences of each gray level are constrained not to exceed a predetermined value. Then a histogram equalization is performed on the input image based on the calculated probability density (or distribution) function. As a result, the mean brightness of the input image does not change significantly by the histogram equalization. Additionally, noise is prevented from being greatly amplified.

Modulation Spectrum Equalization for Improved Robust Speech Recognition

Abstract: We propose novel approaches for equalizing the modulation spectrum for robust feature extraction in speech recognition. Common to all approaches in that the temporal trajectories of the feature parameters are first transformed into the magnitude modulation spectrum. In spectral histogram equalization (SHE) and two-band spectral histogram equalization (2B-SHE), we equalize the histogram of the modulation spectrum for each utterance to a reference histogram obtained from clean training data, or perform the equalization with two sub-bands on the modulation spectrum. In magnitude ratio equalization (MRE), we define the magnitude ratio of lower to higher modulation frequency components for each utterance, and equalize this to a reference value obtained from clean training data. These approaches can be viewed as temporal filters that are adapted to each testing utterance. Experiments performed on the Aurora 2 and 4 corpora for small and large vocabulary tasks indicate that significant performance improvements are achievable for all noise conditions. We also show that additional improvements can be obtained when these approaches are integrated with cepstral mean and variance normalization (CMVN), histogram equalization (HEQ), higher order cepstral moment normalization (HOCMN), or the advanced front-end (AFE). We analyze and discuss the reasons for these improvements from different viewpoints with different sets of data, including adaptive temporal filtering, noise behavior on the modulation spectrum, phoneme types, and modulation spectrum distance measures.

Multispectral Texture Analysis Using Interplane Sum- and Difference-Histograms

Abstract: In this paper we present a new approach for color texture classification which extends the gray level sum- and difference histogram features [8]. Intra- and inter-plane second order features capture the spatial correlations between color bands. A powerful set of features is obtained by non-linear color space conversion to HSV and thresholding operation to eliminate the influence of sensor noise on color information. We present an evaluation of classification performance using four different image sets.

Multi-stream LSTM-HMM decoding and histogram equalization for noise robust keyword spotting

Abstract: Highly spontaneous, conversational, and potentially emotional and noisy speech is known to be a challenge for today’s automatic speech recognition (ASR) systems, which highlights the need for advanced algorithms that improve speech features and models. Histogram Equalization is an efficient method to reduce the mismatch between clean and noisy conditions by normalizing all moments of the probability distribution of the feature vector components. In this article, we propose to combine histogram equalization and multi-condition training for robust keyword detection in noisy speech. To better cope with conversational speaking styles, we show how contextual information can be effectively exploited in a multi-stream ASR framework that dynamically models context-sensitive phoneme estimates generated by a long short-term memory neural network. The proposed techniques are evaluated on the SEMAINE database—a corpus containing emotionally colored conversations with a cognitive system for “Sensitive Artificial Listening”.

Automatic detection method of particle size distribution

Abstract: The invention relates to an automatic detection method of particle size distribution, which is characterized by comprising the following steps: step one, preprocessing images, converting images to be detected into HSV space from RGB space, acquiring chroma, brightness and saturation components of the images to be detected, carrying out Gaussian smoothing filter and histogram equalization to all components and automatically enhancing the brightness, the color and the contrast of the images; step two, carrying out morphological smoothing of color images so as to avoid images caused by the effect of shadow and reflected light; step three, judging a particle area and a centroid thereof and eliminating pseudo-boundary points positioned on the surfaces of particles after completing the process of boundary extraction operation, wherein the pseudo-boundary points have the characteristics of boundary points but are not boundary points ; step four, expanding particles maximumly and carrying outmaximum expansion operation of the particle area, ie dividing the whole material surface into a plurality of parts according to the principle of proximity to one of the particles; step five, calculating particle size by a double-circle method; and step six, calculating particle size distribution Accordingly, the invention provides direct information reference of particle size distribution for follow-up decision operation of industrial process control