Advanced search


Knowledge area




103 results, page 1 of 10

Segmentation of images by color features: a survey

Jair Cervantes Canales Farid García Lamont ASDRUBAL LOPEZ CHAU Lisbeth Rodríguez Mazahua (2018)

En este articulo se hace la revisión del estado del arte sobre la segmentación de imagenes de color

Image segmentation is an important stage for object recognition. Many methods have been proposed in the last few years for grayscale and color images. In this paper, we present a deep review of the state of the art on color image segmentation methods; through this paper, we explain the techniques based on edge detection, thresholding, histogram-thresholding, region, feature clustering and neural networks. Because color spaces play a key role in the methods reviewed, we also explain in detail the most commonly color spaces to represent and process colors. In addition, we present some important applications that use the methods of image segmentation reviewed. Finally, a set of metrics frequently used to evaluate quantitatively the segmented images is shown.

Book part

Color spaces Image segmentation Quantitative evaluation INGENIERÍA Y TECNOLOGÍA

Computing the number of groups for color image segmentation using competitive neural networks and fuzzy c-means

Jair Cervantes Canales Farid García Lamont ASDRUBAL LOPEZ CHAU JOSE SERGIO RUIZ CASTILLA (2016)

Se calcula la cantidad de grupos en que los vectores de color son agrupados usando fuzzy c-means

Fuzzy C-means (FCM) is one of the most often techniques employed for color image segmentation; the drawback with this technique is the number of clusters the data, pixels’ colors, is grouped must be defined a priori. In this paper we present an approach to compute the number of clusters automatically. A competitive neural network (CNN) and a self-organizing map (SOM) are trained with chromaticity samples of different colors; the neural networks process each pixel of the image to segment, where the activation occurrences of each neuron are collected in a histogram. The number of clusters is set by computing the number of the most activated neurons. The number of clusters is adjusted by comparing the similitude of colors. We show successful segmentation results obtained using images of the Berkeley segmentation database by training only one time the CNN and SOM, using only chromaticity data.

Book part

Color characterization Color spaces Competitive neural networks INGENIERÍA Y TECNOLOGÍA

Human mimic color perception for segmentation of color images using a three-layered self-organizing map previously trained to classify color chromaticity

Jair Cervantes Canales Farid García Lamont ASDRUBAL LOPEZ CHAU (2018)

En este trabajo se presenta una propuesta para segmentación de imágenes por características de color utilizando mapas auto organizados.

Most of the works addressing segmentation of color images use clustering-based methods; the drawback with such methods is that they require a priori knowledge of the amount of clusters, so the number of clusters is set depending on the nature of the scene so as not to lose color features of the scene. Other works that employ different unsupervised learning-based methods use the colors of the given image, but the classifying method employed is retrained again when a new image is given. Humans have the nature capability to: (1) recognize colors by using their previous knowledge, that is, they do not need to learn to identify colors every time they observe a new image and, (2) within a scene, humans can recognize regions or objects by their chromaticity features. Hence, in this paper we propose to emulate the human color perception for color image segmentation. We train a three-layered self-organizing map with chromaticity samples so that the neural network is able to segment color images by their chromaticity features. When training is finished, we use the same neural network to process several images, without training it again and without specifying, to some extent, the number of colors the image have. The hue component of colors is extracted by mapping the input image from the RGB space to the HSV space. We test our proposal using the Berkeley segmentation database and compare quantitatively our results with related works; according to the results comparison, we claim that our approach is competitive.

Article

Self-organizing maps Color classification Image segmentation Color spaces INGENIERÍA Y TECNOLOGÍA

Automatic computing of number of clusters for color image segmentation employing fuzzy c-means by extracting chromaticity features of colors

Jair Cervantes Canales Farid García Lamont ASDRUBAL LOPEZ CHAU ARTURO YEE RENDON (2018)

Se propone un enfoque para calcular el numero de grupos en que una imagen de color debe segmentarse utilizando fuzzy c-means

In this paper we introduce a method for color image segmentation by computing automatically the number of clusters the data, pixels, are divided into using fuzzy c-means. In several works the number of clusters is defined by the user. In other ones the number of clusters is computed by obtaining the number of dominant colors, which is determined with unsupervised neural networks (NN) trained with the image’s colors; the number of dominant colors is defined by the number of the most activated neurons. The drawbacks with this approach are as follows: (1) The NN must be trained every time a new image is given and (2) despite employing different color spaces, the intensity data of colors are used, so the undesired effects of nonuniform illumination may affect computing the number of dominant colors. Our proposal consists in processing the images with an unsupervised NN trained previously with chromaticity samples of different colors; the number of the neurons with the highest activation occurrences defines the number of clusters the image is segmented. By training the NN with chromatic data of colors it can be employed to process any image without training it again, and our approach is, to some extent, robust to non-uniform illumination. We perform experiments with the images of the Berkeley segmentation database, using competitive NN and self-organizing maps; we compute and compare the quantitative evaluation of the segmented images obtained with related works using the probabilistic random index and variation of information metrics.

Article

Competitive neural networks Color classification Image segmentation Color spaces INGENIERÍA Y TECNOLOGÍA

Diagnóstico de deficiencias de nitrógeno y maganesio con imágenes digitales

MACIEL REYES FLORES (2013)

Tesis (Maestría en Ciencias, especialista en Edafología).- Colegio de Postgraduados, 2013.

La detección oportuna de deficiencias nutrimentales en hojas de plantas cultivadas permite tomar medidas correctivas inmediatas asi como predecir rendimientos.

Las características espectrales y de textura de las imágenes se pueden utilizar para obtener información y correlacionarlos con el estado nutrimental de elementos esenciales que generan sintomatología similar en hojas de las plantas.

En la presente investigación se estableció un experimento para medir las propiedades espectrales y característica texturales del cultivo de frijol con diferentes concentraciones de nitrógeno y magnesio de imágenes obtenidas con escáner. A partir de los valores de reflectancia se generaron modelos de regresión para asociar la concentración de nitrógeno y magnesio en el tejido vegetal. Además, los valores espectrales se relacionaron con características texturales utilizando redes neuronales para generar clasificadores que permitan conocer el comportamiento de las deficiencias mediante ésta técnica. Los modelos que presentaron mayor grado de asociación con respecto a la interacción de N-Mg fueron el CIE-b (r2 = 0.76), croma (r2 = 0.75), rojo, verde y CIE-L (r2 = 0.73). El mejor clasificador generado por redes neuronales fueron las variables de colores R, G, B, CIE-a con un 89.8% de clasificaciones correctas correspondientes a los tratamientos. Pero también, las combinaciones de variables de colores con texturas produjeron clasificadores adecuados (1) con los espacios de color RGB y CIE-Lab (87.07%) y (2) con las cuatro características texturales y espacios de color RGB y CIELab (88.44). Los valores texturales presentan una mejora considerable cuando se utilizan en combinación con variables de color, que cuando se usan solos. ______________ ABSTRACT: The opportune detection of nutrient deficiencies in plants grown leaves can take immediate corrective action as well as predict yields. The spectral characteristics and texture of the images can be used for information and correlate with nutritional status of essential elements that create similar symptoms in leaves of plants.

In the present investigation, an experiment to measure the spectral properties and textural characteristics of bean cultivation with different concentrations of nitrogen and magnesium from images obtained with scanner. From the reflectance values the regression models were generated to associate the magnesium concentration of nitrogen in the plant tissue. In addition, the spectral values related to textural features using neural networks to generate classifiers that reveal the behavior of the deficiencies by this technique. The models had a higher degree of association with respect to the interaction of N-Mg were the ICD-b (r2 = 0.76), chroma (r2 = 0.75), red, green and CIE-L (r2 = .73). The best classifier neural networks were generated variables colors R, G, B, to a CIE-89.8% of correct classifications for treatments. But also, combinations of variables produced colors with textures suitable classifiers (1) with RGB color spaces and CIE-Lab (87.07%) and (2) with the four textural characteristics, and color spaces RGB and CIELab (88.44) . The textural values presented a considerable improvement when used in combination with variable color, which when used alone.

Master thesis

Reflectancia Discriminación Espacios de color Textura Redes neuronales Reflectance Discrimination Color spaces Texture Neural networks Edafología Maestría CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA

Lattice Algebra Approach to Color Image Segmentation

GONZALO JORGE URCID SERRANO JUAN CARLOS VALDIVIEZO NAVARRO (2012)

This manuscript describes a new technique for segmenting color images in different color spaces based on geometrical properties of lattice auto-associative memories. Lattice associative memories are artificial neural networks able to store a finite set X of n-dimensional vectors and recall them when a noisy or incomplete input vector is presented. The canonical lattice auto-associative memories include the min memory W𝚡𝚡 and the max memory M𝚡𝚡, both defined as square matrices of size n × n. The column vectors of W𝚡𝚡 and M𝚡𝚡, scaled additively by the components of the minimum and maximum vector bounds of X, are used to determine a set of extreme points whose convex hull encloses X. Specifically, since color images form subsets of a finite geometrical space, the scaled column vectors of each memory will correspond to saturated color pixels. Thus, maximal tetrahedrons do exist that enclose proper subsets of pixels in X and such that other color pixels are considered as linear mixtures of extreme points determined from the scaled versions of W𝚡𝚡 and M𝚡𝚡. We provide illustrative examples to demonstrate the effectiveness of our method including comparisons with alternative segmentation methods from the literature as well as color separation results in four different color spaces.

Article

Color image segmentation Color spaces Convex sets Lattice auto-associative memories Linear mixing model Pixel based segmentation Unsupervised clustering CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA FÍSICA ÓPTICA ÓPTICA

Lattice Algebra Approach to Color Image Segmentation

GONZALO JORGE URCID SERRANO JUAN CARLOS VALDIVIEZO NAVARRO (2011)

This manuscript describes a new technique for segmenting color images in different color spaces based on geometrical properties of lattice auto-associative memories. Lattice associative memories are artificial neural networks able to store a finite set X of n-dimensional vectors and recall them when a noisy or incomplete input vector is presented. The canonical lattice auto-associative memories include the min memory Wₓₓ and the max memory Mₓₓ, both defined as square matrices of size n × n. The column vectors of Wₓₓ and Mₓₓ, scaled additively by the components of the minimum and maximum vector bounds of X, are used to determine a set of extreme points whose convex hull encloses X. Specifically, since color images form subsets of a finite geometrical space, the scaled column vectors of each memory will correspond to saturated color pixels. Thus, maximal tetrahedrons do exist that enclose proper subsets of pixels in X and such that other color pixels are considered as linear mixtures of extreme points determined from the scaled versions of Wₓₓ and Mₓₓ. We provide illustrative examples to demonstrate the effectiveness of our method including comparisons with alternative segmentation methods from the literature as well as color separation results in four different color spaces.

Article

Color image segmentation Color spaces Convex sets Lattice auto-associative memories Linear mixing model Pixel based segmentation Unsupervised clustering CIENCIAS FÍSICO MATEMÁTICAS Y CIENCIAS DE LA TIERRA FÍSICA ÓPTICA ÓPTICA

Effects of Colored Light on Growth and Nutritional Composition of Tilapia, and Biofloc as a Food Source

CARLOS ALBERTO OLVERA OLVERA (2020)

Light stimulation and biofloc technology can be combined to improve the efficiency and

sustainability of tilapia production. A 73-day pilot experiment was conducted to investigate the

effect of colored light on growth rates and nutritional composition of the Nile tilapia fingerlings

(Oreochromis niloticus) in biofloc systems. The effect of colored light on the nutritional composition of

bioflocs as a food source for fish was measured. Three groups were illuminated in addition to natural

sunlight with colored light using RGB light emitting diodes (LEDs) with peak wavelengths ( ) of

627.27 nm for red (R), 513.33 nm for green (G), and 451.67 nm for blue (B) light. LED light intensity

was constant (0.832 mW/cm2), and had an 18-h photoperiod of light per day throughout the study.

The control group was illuminated only with natural sunlight (natural). Tilapia had an average initial

weight of 0.242 g. There was a significant effect of colored light on tilapia growth and composition.

The R group showed the best growth rate, highest survival, and highest lipid content. The B group

showed homogeneous growth with the lowest growth rate and lipid content, but the highest protein

level. On the other hand, the biofloc composition was influenced by the green light in the highest

content of lipids, protein, and nitrogen-free extract.

Producción Científica de la Universidad Autónoma de Zacatecas UAZ

Article

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA food science sustainable aquaculture fish production LEDs Light Color

CARACTERIZACIÓN POSCOSECHA DE SELECCIONES DE ZAPOTE MAMEY (Pouteria sapota (Jacq.)H. E. Moore

&

Stearn) PROCEDENTES DEL SOCONUSCO, CHIAPAS

JUAN MANUEL VILLARREAL FUENTES EMILIO HERNANDEZ CLARA PELAYO ZALDIVAR OMAR FRANCO MORA (2014)

Frutos de seis selecciones (S) de zapote mamey del Soconusco, Chiapas; fueron cosechados en madurez fisiológica y madurados en condiciones ambientales (23 grados C y 70 % de HR) por 12 d. Las selecciones presentaron valores máximos de respiración de 31 y 44 mL CO 2kg−1 h−1 con producción de etileno entre 175.9 y 375.5 uL kg−1 h−1. Las selecciones S1 y S2 mantuvieron la mayor firmeza (<20 N) después de seis días de evaluación, menor contenido de fenoles totales (0.5-0.6 mg g−1 de peso fresco) y mejores parámetros de color en pulpa (L*=53, C*= 46 y h= 55). El contenido de sólidos solubles en madurez de consumo fue de 17.5 a 23 Brix y el contenido de los azúcares de 122 a 196 mg g−1; en madurez de consumo en las selecciones evaluadas, sin detectar diferencias significativas entre ellas.

Article

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA Calidad de fruta Respiración Etileno Color Fenoles Firmeza Sólidos solubles

Parámetro CIE (L*, a*, b*) por hojas de caña de azúcar y medidos en longitud de onda que atraen a la mosca pinta Aeneolamia albofasciata (Hemíptera: Cercopidae).

JORGE LUIS LADRÓN DE GUEVARA FUENTES (2015)

Tesis (Maestría en Ciencias, especialista en Agroecosistemas Tropicales).- Colegio de Postgraduados, 2015.

La caña de azúcar forma la agroindustria más importante, durante los ciclos 2014/2015 la derrama económica fue de $49, 008, 560,654.20 mil millones de pesos aproximadamente, los cuales aportan el 26% al PIB. La mosca pinta, puede mermar la producción hasta un 30% lo cual es un golpe grave a la economía del productor, por esta razón es necesario crear trampas que sean más eficientes y selectivas de mosca pinta. Por medio de parámetros con base en CIE (L*, a*, b*) se puede medir el color que crea una longitud de onda que atrae a la mosca pinta. El objetivo fue el de identificar la relación de la acumulación de clorofila con la fertilización y la variedad utilizada que por la incidencia de la luz generan el parámetro CIE (L*, a*, b*) que es más atrayente a la mosca pinta. Se realizaron tres estudios, dos realizados en campo el cual también se aplicaron encuestas y el uno en invernadero para tener el control de las variables de estudio y dosis de fer-tilización. Se determinó que las hojas de caña con parámetros CIE L*= 65.4, a*= -21.97 y b*= 26.19 emiten una longitud de onda menor a 560 nm, que las hace más atrayentes al ataque de la mosca pinta. En cuanto a los productores a muchos les preocupa el crecimiento poblacional de mosca pinta y otros creen que no es una plaga que afecte a sus cultivos. _______________ PARAMETER CIE COLOR (L *, a *, b *) BY SUGAR CANE LEAVES AND MEASURED AT WAVELENGTH THAT ATTRACT THE SPITTLEBUG ADULTS, Aeneolamia albofasciata (Hemiptera : Cercopidae). ABSTRACT: Sugarcane is the most important agro-industry, during cycles 2014 / 2015 the economic impact was $49, 008, 560,654.20 billion pesos, which contribute 26% to GDP. Spittlebug adulta can reduce the production up to 30% which is a serious problem to the economy of the sugarcane producer and mills, for this reason it is necessary to create traps that are more efficient and selec-tive to spittlebug adults. Using parameters based on CIE (L *, a *, b *) color that creates a wave-length that attracts the spittlebug adults can be measured. Aimed to the identify the relationship of the accumulation of chlorophyll with fertilization and used variety generated by the incidence of light by the CIE parameter (L *, a *, b *) which is more attractive to the spittlebug adults. Three studies were carry out, two in field which also applied surveys and one in a greenhouse were to take control of the variables of study and dose of fertilization. We determined than leaves of sugarcane with parameters CIE L * = 65.4, to * = - 21.97 and b * = 26.19 emit a wave-length less than 560 nm, which makes them more attractive to the spittlebug adults attack. As for the producers of spittlebug adults population growth worries many and others believe that it is not a pest affecting their crops.

Master thesis

CIE (L*, a*, b*) Clorofila Color Caña Trampa Chlorophyll Cane Trap Agroecosistemas Tropicales Maestría CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA CIENCIAS AGRARIAS AGRONOMÍA PARASITOLOGÍA VEGETAL