2023年10月6日 · The proposed J-HMMSteg is a simple model-based, minimal-distortion JPEG image steganography technique that is secure and adaptive. It builds HMM image models from complex image statistics (such as the intra-inter block correlations) to link statistical detectability with the cover statistics.

The HMM parameters are estimated b y the EM algorithm. T o classify an image, the classes with maxim um a p osteriori probabilit y are searc hed join tly for all the blo c ks. Applications of the HMM algorithm to do cumen t and aerial image segmen tation sho w that the algorithm outp erforms CAR T TM,L V Q, and Ba y es V Q. I In tro duction F ...

2008年3月20日 · HMMEditor can visualize the profile HMM architecture, transition probabilities, and emission probabilities. Moreover, it provides functions to edit and save HMM and parameters. Furthermore, HMMEditor allows users to align a sequence against the profile HMM and to visualize the corresponding Viterbi path.

We propose a novel method for recognizing temporally or spatially varying patterns using MFCC (mel-frequency ceptral coefficient) and HMM (hidden Markov model). MFCC and HMM have been adopted as de facto standard for speech recognition. It is very useful in modeling time-domain signals with temporally varying characteristics.

Using the versatility of HMMs, let’s try applying them to another problem; Optical Character Recognition. Our goal is to recognize text in an image where the font and font size is known ahead of time. Modern OCR is very good at recognizing documents, but rather poor when recognizing isolated characters.

In this work, we present a new segmentation algorithm that is based on the theory of two-dimensional hidden Markov models (2D-HMM). Unlike most 2D-HMM approaches we do not apply the Viterbi Algorithm, instead we present a computationally efficient algorithm that propagates the state probabilities through the image.

HMM’s can not only be used to predict and classify the random input digit, but also be used to reconstruct the image when the certain parts of the input image are missing.

This study introduces J-HMMSteg, an adaptive and secure JPEG image steganography technique designed for data embedding with minimal distortion. J-HMMSteg employed a block-wise analysis approach to detect shifts in image statistics and was performed in three phases. Firstly, it constructed statistical features of the images by analyzing intra ...

An HMM-HMT model is developed for each texture of interest, with which image segmentation is achieved. Several numerical examples are presented to demonstrate the model, with comparisons to alternative approaches.

We develop a multiclass image segmentation method using hidden Markov Gauss mixture models (HMGMMs) and provide examples of segmentation of aerial images and textures. HMGMMs incorporate supervised learning, fitting the observation probability distribution given each class by a Gauss mixture estimated using vector quantization with a minimum ...