Explore the vast range of titles available.

We identify five rice cultivars by mean of developing an image processing algorithm. After preprocessing operations, 36 colour features in RGB, HSI, HSV spaces were extracted from the images. These 36 colour features were used as inputs in back propagation neural network. The feature selection operations were performed using STEPDISC analysis method. The mean classification accuracy with 36 features for paddy, brown and white rice cultivars acquired 93.3, 98.8, and 100%, respectively. After the feature selection to classify paddy cultivars, 13 features were selected for this study. The highest mean classification accuracy (96.66%) was achieved with 13 features. With brown and white rice, 20 and 25 features acquired the highest mean classification accuracy (100%, for both of them). The optimised neural networks with two hidden layers and 36-6-5-5, 36-9-6-5, 36-6-6-5 topologies were obtained for the classification of paddy, brown, and white rice cultivars, respectively. These structures of neural network had the highest mean classification accuracy for bulk paddy, brown and white rice identification (98.8, 100, and 100%, respectively).

It is necessary to develop a non-destructive technique for kiwifruit quality analysis because the machine injury could lower the quality of fruit and incur economic losses. Bruises are not visible externally owing to the special physical properties of kiwifruit peel. We proposed the hyperspectral imaging technique to inspect the hidden bruises on kiwifruit. The Vis/NIR (408-1,117 nm) hyperspectral image data was collected. Multiple optimal wavelength (682, 723, 744, 810, and 852 nm) images were obtained using principal component analysis on the high dimension spectral image data (wavelength range from 600 nm to 900 nm). The bruise regions were extracted from the component images of the five waveband images using RBF-SVM classification. The experimental results showed that the error of hidden bruises detection on fruits by means of hyperspectral imaging was 12.5%. It was concluded that the multiple optimal waveband images could be used to constructs a multispectral detection system for hidden bruises on kiwifruits.

La estimación del área foliar de la plantas a partir de las dimensiones de las hojas, sin recurrir a métodos destructivos, permite evaluar los factores que afectan el crecimiento de los cultivos de una manera precisa y en intervalos cortos de tiempo. Con el fin de establecer un modelo para calcular el área foliar de la arveja (Pisum sativum L.) en ambientes de trópico alto propios de la Sabana de Bogotá, se sembraron dos lotes de arveja v. 'Santa Isabel' cada uno con 2 ha de extensión en dos semestres diferentes. En cada lote se marcaron 32 puntos para la toma de muestras, de cada punto se escogieron 20 hojas y de cada hoja se tomaron todos los foliolos para medir el largo y el ancho mediante análisis de imágenes. En uno de los lotes se hicieron evaluaciones a los 42 y 62 días después de la siembra; en el otro lote se hizo una única evaluación 72 días después de la siembra. Se estableció que el área de los foliolos y las estípulas de arveja se puede calcular eficientemente mediante modelos alométricos convencionales (largo y ancho) durante las etapas vegetativa y reproductiva del cultivo. El área de estos órganos también se puede estimar con base únicamente en la longitud de la lámina (bajo la forma 0,366L2), modelo con un solo factor que redujo a la mitad el tiempo de evaluación y fue aplicable por igual a los dos ciclos de crecimiento y las dos edades de cultivo. The estimation of foliar area of plants from leaf dimensions, without using destructive methods, allows evaluation of the factors that affect the growth of crops in an precise manner and in short time intervals. In order to establish a model to calculate the foliar area of pea (Pisum sativum L.) in high tropical environments typical of the Sabana of Bogota, two 2-ha plots of 'Santa Isabel' variety peas were sown in each of two different semesters. In each plot 32 points were marked for sampling and at each point 20 leaves were chosen and all leaflets from each leaf were measured for length and width using image analysis. In one plot evaluations were made at 42 and 62 days after sowing; in the other plot only one evaluation was made at 72 days after sowing. It was established that the area of the pea leaflets and stipules can be efficiently calculated using conventional allometric models (length and width) during the vegetative and reproductive stages of the crop. The area of these organs can also be estimated based solely on the length of the lamina (under the formula, 0.336 L2), a model with only one factor that reduced in half the time of evaluation and was applicable equally to both growth cycles and crop ages.

There is a growing requirement for ecosystem science to help inform a deeper understanding of the effects of global climate change and land use change on terrestrial ecosystem structure and function, from small area (plot) to landscape, regional and global scales. To meet these requirements, ecologists have investigated plant growth and carbon cycling processes at plot scale, using biometric methods to measure plant carbon accumulation, and gas exchange (chamber) methods to measure soil respiration. Also at the plot scale, micrometeorologists have attempted to measure canopy- or ecosystem-scale CO2 flux by the eddy covariance technique, which reveals diurnal, seasonal and annual cycles. Mathematical models play an important role in integrating ecological and micrometeorological processes into ecosystem scales, which are further useful in interpreting time-accumulated information derived from biometric methods by comparing with CO2 flux measurements. For a spatial scaling of such plot-level understanding, remote sensing via satellite is used to measure land use/vegetation type distribution and temporal changes in ecosystem structures such as leaf area index. However, to better utilize such data, there is still a need for investigations that consider the structure and function of ecosystems and their processes, especially in mountainous areas characterized by complex terrain and a mosaic distribution of vegetation. For this purpose, we have established a new interdisciplinary approach named 'Satellite Ecology', which aims to link ecology, remote sensing and micrometeorology to facilitate the study of ecosystem function, at the plot, landscape, and regional scale.

A non-destructive Vis-NIR spectroscopy (400-1000 nm) method was developed to evaluate the loss of freshness of sliced and commercially packaged cooked ham and turkey ham without any sample manipulation. The spectra were recorded at 0, 30, 40, and 60 days using a camera, spectral filter (400-1000 nm) and a halogen floodlighting system which had been were developed and calibrated for the purpose. Physico-chemical, biochemical, and microbiological properties such as pH, total volatile basic nitrogen (TVB-N), ATP breakdown compounds, and colony-forming units were determined to predict the degradation of freshness. The image spectra obtained from visible and SW-NIR spectroscopy were related to the storage time of the samples. A PLS-DA model was developed independently for packaged or unpackaged samples using the second derivative of the spectra. Mean R2 prediction obtained for cooked ham was 0.915 and 0.949 for Turkey ham. The technique developed could be applied to monitoring the freshness of commercial packed cooked ham and turkey ham as a non-destructive technique. Further studies will be needed to check the spectra obtained from samples of different commercial brands in order to evaluate more precisely the efficiency of the method.

The effects of microwave assisted drying on banana fruit was evaluated. Water, reducing sugars, and polyphenol contents, as well as poly-phenol-oxidase activity were evaluated along the radial and axial positions in thick slices of banana, according to a properly defined cutting and assaying protocol. The effects of the microwave-assisted drying process were compared to the convective air-assisted drying resulting faster than the conventional process. In particular, the resulting samples were homogeneous in the water content; the contents of reducing sugars were strongly decreased on drying with microwaves; the poly-phenol-oxidase was inactivated by the high temperature produced by the process and thus the polyphenols content remained practically the same as in the fresh product.

This paper describes the course and variation in the brain base arteries in fallow deer. The metrical features of the brain base arteries were determined with an image analysis system. The main sources of blood supply to the brain in fallow deer are internal carotid arteries; vertebral arteries rarely participate in blood supply. The brain base arteries in fallow deer show variation both in their course and in the way of descent of particular vessels. The highest variation was observed in the way of the opening of caudal cerebral arteries. The volume of the arterial circle of brain in fallow deer is similar to the volume of the basilar artery. Considering the correlation between specific parameters, it can be concluded that the volume of the basilar artery is highly correlated with the volume of the posterior part of the arterial circle of the brain, i.e., the volume of the caudal communicating arteries.

The presence of mudskipper eggs in an air-filled chamber was confirmed by direct endoscopic observation of intact burrows of Periophthalmodon schlosseri in a mudflat in Penang, Malaysia. For all five burrows from which video images of egg chambers were successfully obtained, the presence of air was unequivocally demonstrated by the existence of an air-water interface inside the chambers. Of these burrows, eggs were found in two, but not in the others. Eggs were laid uniformly in a monolayer on the inner top surface of the chamber. The much brighter color of the surface mud of the egg chambers than the surrounding mud, irrespective of the presence or absence of the eggs, suggested that the surface mud had been oxidized by deposited air.

A method was developed using scanned computer images and software programs to measure the lesion area on leaves with cucumber anthracnose caused by Colletotrichum orbiculare. After cucumber plants were inoculated with various concentrations of conidia, lesions on diseased leaves were scanned, manipulated with Adobe Photoshop 6.0, and measured using the blob analysis feature in Matrox Inspector 2.2. The method requires relatively low-cost equipment including a scanner, a personal computer, and two programs: Adobe Photoshop 6.0 and Matrox Inspector 2.2. Because stored images are used, the lesion area can be measured as time permits. Processing the images requires about 3 min per sample. The image assessment accurately detected anthracnose lesions on cucumber leaves and could be applied to other foliar necrotic or spot diseases. [PUBLICATION ABSTRACT]

The detection and recognition of objects in images is a key research topic in the computer vision community.  Within this area, face recognition and interpretation has attracted increasing attention owing to the possibility of unveiling human perception mechanisms, and for the development of practical biometric systems.