Color image processing pipeline

Ramanath, Rajeev; Snyder, Wesley E.; Yoo, Yong Keun; Drew, Mark S.

doi:10.1109/msp.2005.1407713

Cited by 315 publications

(184 citation statements)

References 34 publications

Supporting

Mentioning

182

Contrasting

Unclassified

Order By: Relevance

“…Common color spaces include RGB (Süsstrunk, Buckley & Swen, 1999), CMYK (Gatter, 2005), HSL (Levkowitz & Herman, 1993), to mention a few. The application of each one can be found in several works (Vartak & Mankar, 2013;Ramanath, S., Yoo, & Drew, 2005;Bhattacharayya, 2011, andYang, Liu, &Zhang, 2010). They use color space properties focusing in a particular task, exploiting characteristics that can be used for own purposes.…”

Section: Introductionmentioning

confidence: 99%

A Linear Criterion to sort Color Components in Images

Rodriguez¹,

Hernandez²,

Soto-Cajiga³

et al. 2017

ing.inv.

View full text Add to dashboard Cite

The color and its representation play a basic role in Image Analysis process. Several methods can be beneficial whenever they have a correct representation of wave-length variations used to represent scenes with a camera. A wide variety of spaces and color representations is founded in specialized literature. Each one is useful in concrete circumstances and others may offer redundant color information (for instance, all RGB components are high correlated). This work deals with the task of identifying and sorting which component from several color representations offers the majority of information about the scene. This approach is based on analyzing linear dependences among each color component, by the implementation of a new sorting algorithm based on entropy. The proposal is tested in several outdoor/indoor scenes with different light conditions. Repeatability and stability are tested in order to guarantee its use in several image analysis applications. Finally, the results of this work have been used to enhance an external algorithm to compensate the camera random vibrations.Keywords: Linear sorting criterion, color sorting, color analysis, camera vibrations. RESUMENEl color y su representación juegan un papel fundamental en el proceso de análisis de imagen. Varios métodos pueden ser beneficiosos siempre que tengan una representación correcta de las variaciones de longitud de onda usadas para representar la escena. Una amplia variedad de espacios y representaciones de color se basa en la literatura especializada. Cada uno de ellos es útil en circunstancias concretas y puede ofrecer información de color redundante (por ejemplo, todos los componentes RGB están altamente correlacionados). En este trabajo se identifica y clasifica cuál componente ofrece la mayor cantidad de información acerca de la escena, a partir de varias representaciones de color. Este enfoque se basa en el análisis de las dependencias lineales entre cada canal y la implementación de un nuevo algoritmo para clasificar los componentes en base a la entropía. La propuesta se pone a prueba en varias escenas al aire libre y en interiores con diferentes condiciones de luz. La repetitividad y la estabilidad son probadas para garantizar su uso en aplicaciones de análisis de imágenes. Finalmente, los resultados de este trabajo son usados para mejorar un algoritmo externo para la compensación de vibraciones.Palabras Clave: Criterio de clasificación lineal, clasificación de color, análisis de color, vibración de cámaras.

show abstract

Section: Introductionmentioning

confidence: 99%

A Linear Criterion to sort Color Components in Images

Rodriguez¹,

Hernandez²,

Soto-Cajiga³

et al. 2017

ing.inv.

View full text Add to dashboard Cite

show abstract

“…For instance, in image processing applications, a flow of images (data sets) enters the pipeline and must go through several stages such as filters, encoders, and so on [1], [2], [3]. Other examples of such applications are stream-processing applications composed of processing elements [4], or pipelined query operators with precedence constraints [5].…”

Section: Introduction and Related Workmentioning

confidence: 99%

Optimizing Buffer Sizes for Pipeline Workflow Scheduling with Setup Times

Benoît

Nicod

Rehn‐Sonigo

2014

2014 IEEE International Parallel &Amp; Distributed Processing Symposium Workshops

View full text Add to dashboard Cite

Abstract-Mapping linear workflow applications onto a set of homogeneous processors can be optimally solved in polynomial time for the throughput objective with fewer processors than stages. This result even holds true, when setup times occur in the execution and homogeneous buffers are available for the storage of intermediate results. In this kind of applications, several computation stages are interconnected as a linear application graph, and each stage holds a buffer of limited size where intermediate results are stored and a processor setup time occurs when passing from one stage to another. In this paper, we tackle the problem where the buffer sizes are not given beforehand and have to be fixed before the execution to maximize the throughput within each processor. The goal of this work is to minimize the cost induced by the setup times allocating buffers with proportional sizes of each other. We present a closed formula to compute the optimal buffer allocation in the case of nondecreasing setup costs in the linear application. For the case of unsorted setup times, we provide competitive heuristics that are validated via extensive simulation.

show abstract

“…Color image processing systems [1] are used for a variety of purposes, ranging from capturing and rendering scenes in entertainment, industry, scientific exploration and medical praxis [2]. Processing of color imagery for feature and edge extraction [3] underlies several image processing algorithms for pattern recognition in industrial and scientific applications, computer vision systems and image coding methods.…”

Section: Introductionmentioning

confidence: 99%

A Window-Based Self-Organizing Feature Map (SOFM) for Vector Filtering Segmentation of Color Medical Imagery

Stephanakis

Anastassopoulos

Iliadis

2011

Engineering Applications of Neural Networks

View full text Add to dashboard Cite

Abstract. Color image processing systems are used for a variety of purposes including medical imaging. Basic image processing algorithms for enhancement, restoration, segmentation and classification are modified since color is represented as a vector instead of a scalar gray level variable. Color images are regarded as two-dimensional (2-D) vector fields defined on some color space (like for example the RGB space). In bibliography, operators utilizing several distance and similarity measures are adopted in order to quantify the common content of multidimensional color vectors. SelfOrganizing Feature Maps (SOFMs) are extensively used for dimensionality reduction and rendering of inherent data structures. The proposed windowbased SOFM uses as multidimensional inputs color vectors defined upon spatial windows in order to capture the correlation between color vectors in adjacent pixels. A 3x3 window is used for capturing color components in uniform color space (L * u * v * ). The neuron featuring the smallest distance is activated during training. Neighboring nodes of the SOFM are clustered according to their statistical similarity (using the Mahalanobis distance). Segmentation results suggest that clustered nodes represent populations of pixels in rather compact segments of the images featuring similar texture.

show abstract

Color image processing pipeline

Cited by 315 publications

References 34 publications

A Linear Criterion to sort Color Components in Images

A Linear Criterion to sort Color Components in Images

Optimizing Buffer Sizes for Pipeline Workflow Scheduling with Setup Times

A Window-Based Self-Organizing Feature Map (SOFM) for Vector Filtering Segmentation of Color Medical Imagery

Contact Info

Product

Resources

About