Exploring Super-Resolution for Face Recognition

Biometric recognition is part of many aspects of modern society. With the popularization of smartphones, facial recognition gains space in this environment of biometric technologies. With the diversity of image capture devices, of different brands and qualities, the images will not always be in the ideal standard to be recognized. This article tests and compares different scenarios and situations to assess the results obtained by facial recognition in different environments. For this, the quantity method of data analysis was used. In the first scenario, all images were submitted without changes. In the following, we have the reduction of image resolution, which may or may not be followed by enlargement to the original resolution via bicubic interpolation or through the Image Super-Resolution algorithm, these images can be all, or only that undergo tests. Results indicate that the first scenario obtained the best performance, followed by only the tests images change. The worst performance occurs where the properties of all images are affected. In situations where there is a reduction and enlargement are optional, the enlargement option performs better, so the bicubic enlargement has an advantage over the ISR, the situation in which only the reduction occurs has the worst performance.

Single image super resolution based on multi-scale structure and non-local smoothing

In this paper, we propose a hybrid super-resolution method by combining global and local dictionary training in the sparse domain. In order to present and differentiate the feature mapping in different scales, a global dictionary set is trained in multiple structure scales, and a non-linear function is used to choose the appropriate dictionary to initially reconstruct the HR image. In addition, we introduce the Gaussian blur to the LR images to eliminate a widely used but inappropriate assumption that the low resolution (LR) images are generated by bicubic interpolation from high-resolution (HR) images. In order to deal with Gaussian blur, a local dictionary is generated and iteratively updated by K-means principal component analysis (K-PCA) and gradient decent (GD) to model the blur effect during the down-sampling. Compared with the state-of-the-art SR algorithms, the experimental results reveal that the proposed method can produce sharper boundaries and suppress undesired artifacts with the present of Gaussian blur. It implies that our method could be more effect in real applications and that the HR-LR mapping relation is more complicated than bicubic interpolation.

Analysis of Medical Image Resizing Using Bicubic Interpolation Algorithm

Image interpolation is the most basic requirement for many image processing tasks such as medical image processing. Image interpolation is a technique used in resizing an image. To change the image size, each pixel in the new image must be remapped to a location in the old image to calculate the new pixel value. There are many algorithms available for determining the new pixel value, most of which involve some form of interpolation between the closest pixels in the old image. In this paper, we use the Bicubic interpolation algorithm to change the size of medical images from the Messidor dataset and then analyze it by measuring it using three parameters Mean Square Error (MSE), Root Mean Squared Error (RMSE), and Peak Signal-to-Noise Ratio (PSNR), and compare the results with Bilinear and Nearest-neighbor algorithms. The results showed that the Bicubic algorithm is better than Bilinear and Nearest-neighbor and the larger the image dimensions are resized, the higher the degree of similarity to the original image, but the level of computation complexity also increases.

Teknik Interpolasi Bikubik untuk Memperbesar Gambar Hasil Pemetaan Suhu dari Sensor MLX90640 pada Praktikum Mikrokontroller

The occurrence of various disruptions and damage to equipment and electrical installations begins with a significant temperature increase in it. The temperature increasing in electrical equipment and installations will also increase the consumption of energy or power required. Previous technology used a temperature sensor and current sensor which had to be installed in the environment to be monitored. The temperature measurement system without touching the surface which is measured using infrared rays is a new breakthrough that really helps maintenance and repair. Also with the existence of a temperature sensor arranged in an array, it can map the existing temperature so that it can provide a better picture for analyzing the symptoms that occur, compared to using a temperature sensor that measures one point only. A temperature imaging camera is currently very expensive, making procurement a bit difficult for laboratories dealing with electrical equipment and installations. In this research, we will try to make an inexpensive temperature imaging camera using the MLX90640 sensor and the ESP32 microcontroller. Bicubic interpolation is used to enlarge the resulting image obtained by the MLX90640 sensor. The MATLAB program is used to simulate and create an overall temperature imaging camera system. Tested and compared with two other interpolation methods to ensure that bicubic interpolation can produce better magnified images.