During the last few decades, many studies have been performed on the early detection of cancer using noninvasive or minimally invasive techniques in lieu of traditional excisional biopsy. Early detection can make an immense difference because cancer treatment is often simpler and more effective when diagnosed at an early stage. Cancer detecting methods may help physicians to diagnose cancer, to dissect the malignant region with a safe margin, and to evaluate the tumor bed after resection. In this paper, the advanced hyperspectral imaging system has been assessed using infrared wavelengths region for tumor detection. We were able to identify an appropriate wavelength region for cancer detection, spatially resolved images, and highlight the differences in reflectance properties of cancerous versus non‐cancerous tissues. The capability of this instrument was demonstrated by observing gastric tumors in 10 human subjects. The spectral signatures were extracted and evaluated in cancerous and non‐cancerous tissues. Processing means with the standard deviation of the spectral diagram, support vector machine, and first derivatives and integral of in spectral diagram were proposed to enhance and detect the cancerous regions. The first derivatives in spectral region between 1226–1251 nm and 1288–1370 nm were proposed as criteria that successfully distinguish between non‐cancerous and cancerous tissue. The results of this study will lead to advances in the optical diagnosis of cancer. (Cancer Sci 2011; 102: 852–857)

A low-cost, small, lightweight hyperspectral sensor system that can be loaded onto small unmanned autonomous vehicle (UAV) platforms has been developed for the acquisition of aerial hyperspectral data. Safe and easy observation is possible under unstable illumination conditions by using lightweight and autonomous cruising. The hyperspectral sensor system, equipped with a 256-band hyperspectral sensor covering a spectral range from 340-763 nm, a GPS and a data logger, is 400 g in total weight. The acquisition period for each sampling, 768 bytes, is 100 ms. The aerial hyperspectral data of rice paddies are collected under cloudy weather. The flight altitude from the ground is 10 m, and the cruising speed is 2 m/s. The high-accuracy estimation of the chlorophyll densities is confirmed, even under unstable illumination conditions, by frequent monitoring of the illumination level and the chlorophyll indices, based on the red-edge (RE) and near infrared (NIR) spectral ranges.

Color enhancement of multispectral images is useful to visualize the image’s spectral features. Previously, a color enhancement method, which enhances the feature of a specified spectral band without changing the average color distribution, was proposed. However, sometimes the enhanced features are indiscernible or invisible, especially when the enhanced spectrum lies outside the visible range. In this paper, we extended the conventional method for more effective visualization of the spectral features both in visible range and non-visible range. In the proposed method, the user specifies both the spectral band for extracting the spectral feature and the color for visualization respectively, so that the spectral feature is enhanced with arbitrary color. The proposed color enhancement method was applied to different types of multispectral images where its effectiveness to visualize spectral features was verified.

Low-altitude hyperspectral observation systems are promising sensing tools for acquisition of optical remote-sensing data under the humid subtropical climate in Japan. The system is also capable of acquiring leaf-scale optical information free from atmospheric effect. However, the leaf-scale hyperspectral data are affected by shading and various illumination conditions such that it is difficult to obtain consistent characteristics of the spectral information. The aim of this article is the extraction of Lambert coefficients as an inherent leaf spectral profile. In this work, we propose a dichromatic model-based principal component analysis on hyperspectral data by utilizing leaf-scale hyperspectral data in order to diminish the spectral difference caused by the illumination condition and bidirectional reflectance distribution function. The results show that indices of chlorophyll content based on the estimated Lambert coefficients are consistent with the growth stages of a paddy field, whether the illumination condition is clear sky or overcast.

Low-altitude hyperspectral observation systems using aerial observation with unmanned aerial vehicles (UAVs) have advantages over satellite systems with respect to frequency, accuracy, and spatial resolution. Although low-cost lightweight UAVs have become available in recent years, the current price ranges of lightweight pushbroom and snapshot hyperspectral sensors remain high. For sustainable operation of UAV-mounted hyperspectral sensing, the challenge in production has been shifted from the size and weight to the cost of the lightweight hyperspectral sensors. In this paper, we develop a low-cost, lightweight whiskbroom hyperspectral imaging system. The gross weight of the sensor is 1200 g. The spectral range of the 256-band spectrometer extends from 340 to 750 nm with a 14-nm spectral resolution. The viewing angle across the flight direction is controlled by the rotation of an eight-sided polygon mirror. When the exposure time, flight altitude, flight speed, and focal length of the optical lens are 3.2 ms, 10 m, 10 m/s, and 8 mm, respectively, then the estimated values of the swath and the area coverage per second are 13.4 m and 134.1 $\hbox{m}^2$/s, respectively. The spatial resolution is 0.97 (m) (flight direction) $\times$ 0.46 (m) (scanning direction). In preliminary close-range measurements with a 3.2-ms exposure time per area and a 1224-ms rotation period of the polygon mirror, the reflected light from 12 areas of a printed checkered color pattern in the moving direction were measured. We found that the calculated reflectance based on the measurements is spatially consistent and spectrally accurate.

Chlorophyll content is one of the essential parameters to assess the growth process of the fruit trees. This present study developed a model for estimation of canopy averaged chlorophyll content (CACC) of pear trees using the convolutional auto-encoder (CAE) features of hyperspectral data. This study also demonstrated the inspection of anomaly among the trees by employing multi-dimensional scaling (MDS) on the CAE features and detected outlier trees prior to fit nonlinear regression models. These outlier trees were excluded from the further experiments which helped in improving the prediction performance of CACC. Gaussian process regression (GPR) and support vector regression (SVR) techniques were investigated as nonlinear regression models and used for prediction of CACC. The CAE features were proven to be providing better prediction of CACC when compared with the direct use of hyperspectral bands or vegetation indices as predictors. The CACC prediction performance was improved with the exclusion of the outlier trees during training of the regression models. It was evident from the experiments that GPR could predict the CACC with better accuracy compared to SVR. In addition, the reliability of the tree canopy masks, which were utilized for averaging the features' values for a particular tree, was also evaluated.