Unsupervised texture classification using vector quantization and deterministic relaxation neural network
TL;DR: This paper describes the use of a neural network architecture for classifying textured images in an unsupervised manner using image-specific constraints using an energy function corresponding to the a posteriori probability.
read more
Abstract: This paper describes the use of a neural network architecture for classifying textured images in an unsupervised manner using image-specific constraints. The texture features are extracted by using two-dimensional (2-D) Gabor filters arranged as a set of wavelet bases. The classification model comprises feature quantization, partition, and competition processes. The feature quantization process uses a vector quantizer to quantize the features into codevectors, where the probability of grouping the vectors is modeled as Gibbs distribution. A set of label constraints for each pixel in the image are provided by the partition and competition processes. An energy function corresponding to the a posteriori probability is derived from these processes, and a neural network is used to represent this energy function. The state of the network and the codevectors of the vector quantizer are iteratively adjusted using a deterministic relaxation procedure until a stable state is reached. The final equilibrium state of the vector quantizer gives a classification of the textured image. A cluster validity measure based on modified Hubert index is used to determine the optimal number of texture classes in the image.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Contour and Texture Analysis for Image Segmentation
TL;DR: This paper provides an algorithm for partitioning grayscale images into disjoint regions of coherent brightness and texture, and introduces a gating operator based on the texturedness of the neighborhood at a pixel to facilitate cue combination.
Image processing with neural networks–a review
TL;DR: The various applications of neural networks in image processing are categorised into a novel two-dimensional taxonomy for image processing algorithms and their specific conditions are discussed in detail.
1.2K
A b c d e f g ...
SD Shafran,JM Conly +1 more
TL;DR: This study showed that serum adiponectin significantly decreased during the sixmonth follow up in military service compared to baseline levels, and was even shown in subjects that experienced a 5-10 % weight loss after six-months.
MEGA---the maximizing expected generalization algorithm for learning complex query concepts
Edward Y. Chang,Beitao Li +1 more
TL;DR: This study proposes a query-concept learner that learns query criteria through an intelligent sampling process, and proposes the maximizing expected generalization algorithm (MEGA), which converges to target concepts quickly by its two complementary steps: sample selection and concept refinement.
40
Image Segmentation by Relaxation Using Constraint Satisfaction Neural Network
TL;DR: These new segmentation algorithms are based on interplay of additional constraints, of varying the organization of the network or modifying the relaxation scheme, and are tested comparatively on a bank of test images as well as real world images.
22
References
Neural networks and physical systems with emergent collective computational abilities
TL;DR: A model of a system having a large number of simple equivalent components, based on aspects of neurobiology but readily adapted to integrated circuits, produces a content-addressable memory which correctly yields an entire memory from any subpart of sufficient size.
19K
An Algorithm for Vector Quantizer Design
Y. Linde,A. Buzo,Robert M. Gray +2 more
TL;DR: An efficient and intuitive algorithm is presented for the design of vector quantizers based either on a known probabilistic model or on a long training sequence of data.