Urine tests are performed by using an off-the-shelf reference sheet to compare the color of test strips. However, the tabular representation is difficult to use and more prone to visual errors, especially when the reference color-swatches to be compared are spatially apart. Thus, making it is difficult to distinguish between the subtle differences of shades on the reagent pads. This manuscript represents a new arrangement of reference arrays for urine test strips (urinalysis). Reference color swatches are grouped in a doughnut chart, surrounding each reagent pad on the strip. The urine test can be evaluated using naked eye by referring to the strip with no additional sheet necessary. Along with this new strip, an algorithm for smartphone based application is also proposed as an alternative to deliver diagnostic results. The proposed colorimetric detection method evaluates the captured image of the strip, under various color spaces and evaluates ten different tests for urine. Thus, the proposed system can deliver results on the spot using both naked eye and smartphone. The proposed scheme delivered accurate results under various environmental illumination conditions without any calibration requirements, exhibiting performances suitable for real-life applications and an ease for a common user.

Recent improvements in imaging sensors and computing units have led to the development of a range of image-based human–machine interfaces (HMIs). An important approach in this direction is the use of dynamic hand gestures for a gesture-based interface, and some methods have been developed to provide real-time hand skeleton generation from depth images for dynamic hand gesture recognition. Towards this end, we propose a skeleton-based dynamic hand gesture recognition method that divides geometric features into multiple parts and uses a gated recurrent unit-recurrent neural network (GRU-RNN) for each feature part. Because each divided feature part has fewer dimensions than an entire feature, the number of hidden units required for optimization is reduced. As a result, we achieved similar recognition performance as the latest methods with fewer parameters.

Camera-based blind-spot detection systems improve the shortcomings of radar-based systems for accurately detecting the position of a vehicle. However, as with many camera-based applications, the detection performance is insufficient in a low-illumination environment such as at night. This problem can be solved with augmented nighttime images in the training data but acquiring them and annotating the additional images are cumbersome tasks. Therefore, we propose a framework that converts daytime images into synthetic nighttime images using a generative adversarial network and that augments the synthetic images for the training process of the vehicle detector. A public dataset comprising different viewpoints of target images was used to easily obtain the images required for training the generative adversarial network. Experiments on a real nighttime dataset demonstrate that the proposed framework improved the detection performance considerably in comparison with using daytime images only.

The separation of circulating tumor cells (CTCs) from the peripheral blood is an important issue that has been highlighted because of their high clinical potential. However, techniques that depend solely on tumor-specific surface molecules or just the larger size of CTCs are limited by tumor heterogeneity. Here, we present a slanted weir microfluidic device that utilizes the size and deformability of CTCs to separate them from the unprocessed whole blood. By testing its ability using a highly invasive breast cancer cell line, our device achieved a 97% separation efficiency, while showing an 8-log depletion of erythrocytes and 5.6-log depletion of leukocytes. We also developed an image analysis tool that was able to characterize the various morphologies and differing deformability of the separating cells. From the results, we believe our system possesses a high potential for liquid biopsy, aiding future cancer research.

An eye detection method for facial images using Zernike moments with a support vector machine (SVM) is proposed. Eye/non-eye patterns are represented in terms of the magnitude of Zernike moments and then classified by the SVM. Due to the rotation-invariant characteristics of the magnitude of Zernike moments, the method is robust against rotation, which is demonstrated using rotated images from the ORL database. Experiments with TV drama videos showed that the proposed method achieved a 94.6% detection rate, which is a higher performance level than that achievable by the method that uses gray values with an SVM.

Video synopsis allows us to analyze security videos efficiently by condensing or shortening a long video into a short one. To generate a condensed video, moving objects (a.k.a. object tubes) in the video are rearranged in the temporal domain using a predefined objective function. The objective function consists of several energy terms which play important roles in making a visually appealing condensed video. One of the energy terms, collision energy, creates a bottleneck in the computation because it requires two object tubes to calculate the degree of collision between them. Existing approaches try to reduce the computation time of the collision energy calculation by reducing the number of tubes processed at once. However, those approaches are not sufficient to generate condensed video when the number of object tubes becomes large. In this letter, we propose a fast Fourier transform (FFT)-based parallelized tube rearrangement algorithm. To take advantage of both parallel processing and FFT, we represent object tubes as 3D binary matrices (occupation matrices). An objective function of the tube rearrangement problem is defined on the occupation matrix, and a starting position for each tube in the temporal domain is then determined by optimizing the objective function. Throughout the experiments, the proposed algorithm took a much shorter time to condense the video than existing algorithms, while other performance metrics were similar.