Intaek Kim

MULTISPECTRAL DETECTION OF FECAL CONTAMINATION ON APPLES BASED ON HYPERSPECTRAL IMAGERY: PART I. APPLICATION OF VISIBLE AND NEAR–INFRARED REFLECTANCE IMAGING

Fecal contamination of apples is an important food safety issue. To develop automated methods to detect such contamination, a recently developed hyperspectral imaging system with a range of 450 to 851 nm was used to examine reflectance images of experimentally contaminated apples. Fresh feces from dairy cows were applied simultaneously as a thick patch and as a thin, transparent (not readily visible to the human eye), smear to four cultivars of apples (Red Delicious, Gala, Fuji, and Golden Delicious). To address differences in coloration due to environmental growth conditions, apples were selected to represent the range of green to red colorations. Hyperspectral images of the apples and fecal contamination sites were evaluated using principal component analysis with the goal of identifying two to four wavelengths that could potentially be used in an on-line multispectral imaging system. Results indicate that contamination could be identified using either three wavelengths in the green, red, and NIR regions, or using two wavelengths at the extremes of the NIR region under investigation. The three wavelengths in the visible and near-infrared regions offer the advantage that the acquired images could also be used commercially for color sorting. However, detection using the two NIR wavelengths was found to be less sensitive to variations in apple coloration. For both sets of wavelengths, thick contamination could easily be detected using a simple threshold unique to each cultivar. In contrast, results suggest that more computationally complex analyses, such as combining threshold detection with morphological filtering, would be necessary to detect thin contamination spots using reflectance imaging techniques.

Analysis of hyperspectral fluorescence images for poultry skin tumor inspection

We present a hyperspectral fluorescence imaging system with a fuzzy inference scheme for detecting skin tumors on poultry carcasses. Hyperspectral images reveal spatial and spectral information useful for finding pathological lesions or contaminants on agricultural products. Skin tumors are not obvious because the visual signature appears as a shape distortion rather than a discoloration. Fluorescence imaging allows the visualization of poultry skin tumors more easily than reflectance. The hyperspectral image samples obtained for this poultry tumor inspection contain 65 spectral bands of fluorescence in the visible region of the spectrum at wavelengths ranging from 425 to 711 nm. The large amount of hyperspectral image data is compressed by use of a discrete wavelet transform in the spatial domain. Principal-component analysis provides an effective compressed representation of the spectral signal of each pixel in the spectral domain. A small number of significant features are extracted from two major spectral peaks of relative fluorescence intensity that have been identified as meaningful spectral bands for detecting tumors. A fuzzy inference scheme that uses a small number of fuzzy rules and Gaussian membership functions successfully detects skin tumors on poultry carcasses. Spatial-filtering techniques are used to significantly reduce false positives.

MULTISPECTRAL DETECTION OF FECAL CONTAMINATION ON APPLES BASED ON HYPERSPECTRAL IMAGERY: PART II. APPLICATION OF HYPERSPECTRAL FLUORESCENCE IMAGING

Pathogenic E. coli contamination in unpasteurized apple juice or cider is thought to originate from animal feces, and fecal contamination of apples has been recognized by the FDA as an important health issue. In a companion article, reflectance imaging techniques were shown inadequate for the detection of thin smears of feces applied to apples. The objective of this study was to evaluate the use of fluorescence imaging techniques to detect fecal contamination on apple surfaces. A hyperspectral imaging system based on a spectrograph, camera, and UV light source was used to obtain hyperspectral images of Red Delicious, Fuji, Golden Delicious, and Gala apples. Fresh dairy feces were applied to each apple as both a thick patch and as a thin smear. Results indicate that multispectral fluorescence techniques can be used to effectively detect fecal contamination on apple surfaces. Both principal component analysis and examination of emission maxima identified the same four multispectral bands (450, 530, 685, and 735 nm) as being the optimal bands to allow discrimination of contaminated apple surfaces. Furthermore, the simple two-band ratio (e.g., 685 to 450 nm) reduced the variation in normal apple surfaces while accentuating differences between contaminated and uncontaminated areas. Because of the limited sample size, delineation of an optimal detection scheme is beyond the scope of the current study. However, the results suggest that use of multispectral fluorescence techniques for detection of fecal contamination on apples in a commercial setting may be feasible.

DETECTION OF SKIN TUMORS ON CHICKEN CARCASSES USING HYPERSPECTRAL FLUORESCENCE IMAGING

This article presents a method for detecting skin tumors on chicken carcasses using hyperspectral fluorescence imaging data, which provide fluorescence information in both spectral and spatial dimensions. Since these two kinds of information are complementary to each other, it is necessary to exploit them in a synergistic manner. Chicken carcasses are examined first using spectral information, and the results are used to determine candidate regions for skin tumors. Next, a spatial classifier selects the real tumor spots from the candidate regions. It was shown that the method detected chicken carcasses with tumors, but failed to detect some tumors that were smaller than 3 mm in diameter. This study uncovered meaningful spectral bands for detecting tumors using hyperspectral imaging data. A detection system based on this method can improve the detection rate, and processing time can also be reduced, because the detection procedure is simplified by using a limited number of features, which reduces computational complexity. The resultant detection rate, false positive rate, and missing rate of the proposed method are 76%, 28%, and 24%, respectively.

A blind watermarking technique using wavelet transform

In this paper, we propose an effective watermarking algorithm for copyright protection. This is a blind watermarking which can confirm the copyright without the original image. The original image is transformed using wavelet transform and flags are created with the secret key. The secret key is the thing we need to extract the flags and compare the extracted flags with the original flags that are created during the watermark embedding procedure. To criticize the robustness of this scheme we compared the extracted flag with the original flag after several attacks such as JPEG compression, collusion, resize and noise addition. The results show that the proposed watermarking algorithm has excellent robustness against various watermark attacks with the high quality of the watermarked image.

A fuzzy time series prediction method based on consecutive values

This paper presents a time series prediction method using a fuzzy rule-based system. In conventional methods, predicting x(n+k) requires past data such as x(n), x(n-l), ...x(n-m), where k and m are positive integers. However, a serious problem of those methods is that they cannot properly handle non-stationary data whose long-term mean is floating. To cope with this, a new learning method utilizing the difference of consecutive values in a time series is suggested. Computer simulations showed improved results for various time series.

Poultry skin tumor detection in hyperspectral images using radial basis probabilistic neural network

This paper presents a method for detecting poultry skin tumors using hyperspectral fluorescence image. New feature space is generated by the ratio of intensities of two bands, the combination of images such that their intensity ratios yield the least false detection rate is selected by minimizing overlap area of normal and tumor’s PDFs. Four feature images are chosen and presented as an input to a classifier based on the radial basis probability neural network. The classifier categorizes the input with three classes, where one is for tumor and two for normal skin pixels. The classification result based on this method shows the improved performance in that the number of false classification is reduced.

Multi-Target Tracking Using Color Information

—For security purposes, it is prerequisite to track multiple targets efficiently. Most of the current implementation uses Kalman filter and color information independently. The proposed method combines extended Kalman filter and color information for tracking multiple objects under high occlusion. For tracking, the first thing done is the object detection. The background model used to segment foreground from background is spatio-temporal Gaussian mixture model (STGMM). Tracking consists of two steps: independent object tracking and occluded object tracking. For independent object tracking we exploit extended Kalman filter, whereas for occluded object tracking, color information attribute is used. The system was tested in real world application and successful results were obtained.

Spatio-temporal Gaussian Mixture Model for Background Modeling

Background subtraction is widely employed in the detection of moving objects when background does not show much dynamic behavior. Many background models have been proposed by researchers. Most of them analyses only temporal behavior of pixels and ignores spatial relations of neighborhood that may be a key to better separation of foreground from background when background has dynamic activities. To remedy, some researchers proposed spatio-temporal approaches usually in the block-based framework. Two recent reviews[1, 2] showed that temporal kernel density estimation(KDE) method and temporal Gaussian mixture model(GMM) perform about equally best among possible temporal background models. Spatio-temporal version of KDE was proposed. However, for GMM, explicit extension to spatio-temporal domain is not easily seen in the literature. In this paper, we propose an extension of GMM from temporal domain to spatio-temporal domain. We applied the methods to well known test sequences and found that the proposed outperforms the temporal GMM.

Dimensionality reduction of hyperspectral images using kernel ICA

Computational burden due to high dimensionality of Hyperspectral images is an obstacle in efficient analysis and processing of Hyperspectral images. In this paper, we use Kernel Independent Component Analysis (KICA) for dimensionality reduction of Hyperspectraql images based on band selection. Commonly used ICA and PCA based dimensionality reduction methods do not consider non linear transformations and assumes that data has non-gaussian distribution. When the relation of source signals (pure materials) and observed Hyperspectral images is nonlinear then these methods drop a lot of information during dimensionality reduction process. Recent research shows that kernel-based methods are effective in nonlinear transformations. KICA is robust technique of blind source separation and can even work on near-gaussina data. We use Kernel Independent Component Analysis (KICA) for the selection of minimum number of bands that contain maximum information for detection in Hyperspectral images. The reduction of bands is basd on the evaluation of weight matrix generated by KICA. From the selected lower number of bands, we generate a new spectral image with reduced dimension and use it for hyperspectral image analysis. We use this technique as preprocessing step in detection and classification of poultry skin tumors. The hyperspectral iamge samples of chicken tumors used contain 65 spectral bands of fluorescence in the visible region of the spectrum. Experimental results show that KICA based band selection has high accuracy than that of fastICA based band selection for dimensionality reduction and analysis for Hyperspectral images.