Hierarchical Color Quantization with a Neural Gas Model Based on Bregman Divergences

Kompresi citra dapat dilakukan dengan menggunakan color quantization di mana dengan mengurangi jumlah warna yang terdapat pada citra maka akan dapat mengurangi jumlah bit yang digunakan untuk merepresentasikan warna – warna tersebut. Semakin rendah jumlah warna yang dikurangi dalam rangka mencapai rasio kompresi yang optimal berdampak pada terdegradasinya kualitas dari citra. Secara umum color quantization menggunakan model clustering dalam proses pembentukan color palette yang akan digunakan sebagai referensi pada saat kuantisasi. Penelitian ini menggunakan model clustering berdasarkan nilai max variance pada channel RGB secara terpisah. Proses clustering dilakukan dengan membelah populasi cluster sebelumnya menggunakan nilai mean dari channel RGB yang memiliki nilai variance tertinggi. Color palette kemudian dibentuk menggunakan centroid hasil dari proses clustering. Percobaan pada beberapa citra uji dengan format 32bpp yang kemudian dikompresi menggunakan kuantisasi warna pada format 8bpp dan 4bpp memberikan kualitas dan rasio kompresi yang cukup baik yang diukur menggunakan ukuran MSE, PSNR dan CR di mana nilai MSE yang diperoleh berkisar 3.87 sampai 6.3 pada kuantisasi 8bpp dan 13.39 sampai 19.62 pada kuantisasi 4bpp. Sedangkan rasio kompresi yang diperoleh adalah sebesar 1.44 sampai 2.09 pada kuantisasi 8bpp dan 2.87 sampai 4.23 pada kuantisasi 4bpp. AbstractImage compression can be done by using color quantization where by reducing the number of colors contained in the image it can reduce the number of bits used to represent the colors. The lower the number of colors reduced in order to achieve the optimal compression ratio has an impact on the quality of the image. In general, color quantization uses clustering models in the process of constructing color palette that will be used as a reference during quantization. This study uses a clustering model based on the max variance value on the RGB channel separately. The clustering process is done by dividing the previous cluster population using the mean value of the RGB channel which has the highest variance value. The color palette is then formed using centroids resulting from the clustering process. Experiments on some test images in 32bpp format which are then compressed using color quantization in 8bpp and 4bpp formats provide a fairly good quality and compression ratio with MSE, PSNR and CR assessment where the MSE values obtained ranged from 3.87 to 6.3 at 8bpp quantization and 13.39 to 19.62 at 4bpp quantization. While the compression ratio obtained is 1.44 to 2.09 at 8bpp quantization and 2.87 to 4.23 at 4bpp quantization

Download Full-text

Representation, abstraction, and simple-minded sophisticates

Behavioral and Brain Sciences ◽

10.1017/s0140525x19002942 ◽

2020 ◽

Vol 43 ◽

Author(s):

Peter Dayan

Keyword(s):

Decision Theory ◽

Predictive Coding ◽

Bayesian Decision Theory ◽

Bayesian Decision ◽

Model Based ◽

Model Free

Abstract Bayesian decision theory provides a simple formal elucidation of some of the ways that representation and representational abstraction are involved with, and exploit, both prediction and its rather distant cousin, predictive coding. Both model-free and model-based methods are involved.

Download Full-text

Quantitative Model-Based Image Analysis of NuMa Distribution Links Nuclear Organization with Cell Phenotype

Microscopy and Microanalysis ◽

10.1017/s1431927600028968 ◽

2001 ◽

Vol 7 (S2) ◽

pp. 578-579

Author(s):

David W. Knowles ◽

Sophie A. Lelièvre ◽

Carlos Ortiz de Solόrzano ◽

Stephen J. Lockett ◽

Mina J. Bissell ◽

...

Keyword(s):

Image Analysis ◽

Mammary Epithelial Cells ◽

Nuclear Organization ◽

Critical Role ◽

Quantitative Model ◽

Mammary Epithelial ◽

Cell Phenotype ◽

Proliferating Cells ◽

Mitotic Apparatus ◽

Model Based

The extracellular matrix (ECM) plays a critical role in directing cell behaviour and morphogenesis by regulating gene expression and nuclear organization. Using non-malignant (S1) human mammary epithelial cells (HMECs), it was previously shown that ECM-induced morphogenesis is accompanied by the redistribution of nuclear mitotic apparatus (NuMA) protein from a diffuse pattern in proliferating cells, to a multi-focal pattern as HMECs growth arrested and completed morphogenesis . A process taking 10 to 14 days.To further investigate the link between NuMA distribution and the growth stage of HMECs, we have investigated the distribution of NuMA in non-malignant S1 cells and their malignant, T4, counter-part using a novel model-based image analysis technique. This technique, based on a multi-scale Gaussian blur analysis (Figure 1), quantifies the size of punctate features in an image. Cells were cultured in the presence and absence of a reconstituted basement membrane (rBM) and imaged in 3D using confocal microscopy, for fluorescently labeled monoclonal antibodies to NuMA (fαNuMA) and fluorescently labeled total DNA.

Download Full-text