In recent years, the preservation of handwritten historical documents and scripts archived by digitized images has been gradually emphasized. However, the selection of different thicknesses of the paper for printing or writing is likely to make the content of the back page seep into the front page. In order to solve this, a cost-efficient document image system is proposed. In this system, the authors use Adaptive Directional Lifting-Based Discrete Wavelet Transform to transform image data from spatial domain to frequency domain and perform on high and low frequencies, respectively. For low frequencies, the authors use local threshold to remove most background information. For high frequencies, they use modified Least Mean Square training algorithm to produce a unique weighted mask and perform convolution on original frequency, respectively. Afterward, Inverse Adaptive Directional Lifting-Based Discrete Wavelet Transform is performed to reconstruct the four subband images to a resulting image with original size. Finally, a global binarization method, Otsu’s method, is applied to transform a gray scale image to a binary image as the output result. The results show that the difference in operation time of this work between a personal computer (PC) and Raspberry Pi is little. Therefore, the proposed cost-efficient document image system which performed on Raspberry Pi embedded platform has the same performance and obtains the same results as those performed on a PC.

Rain removal is essential for achieving autonomous driving because it preserves the details of objects that are useful for feature extraction and removes the rain structures that hinder feature extraction. Based on a linear superposition model in which the observed rain image is decomposed into two layers, a rain layer and a non-rain layer, conventional rain removal methods estimate these two layers alternatively from an observed single image based on prior modeling. However, the prior knowledge used for the rain structures is not always correct because various types of rain structures can be observed in the rain images, which results in inaccurate rain removal. Therefore, in this article, a novel rain removal method based on the use of a scribbled rain image set and a new shrinkage-based sparse coding model is proposed. The scribbled rain images have information about which pixels have rain structures. Thus, various types of rain structures can be modeled, owing to the abundance of rain structures in the rain image set. To detect the rain regions, two types of approaches, one based on reconstruction error comparison (REC) via a learned rain dictionary and the other based on a deep convolutional neural network (DCNN), are presented. With the rain regions, the proposed shrinkage-based sparse coding model determines how much to reduce the sparse codes of the rain dictionary and maintain the sparse codes of the non-rain dictionary for accurate rain removal. Experimental results verified that the proposed shrinkage-based sparse coding model could remove rain structures and preserve objects’ details due to the REC- or DCNN-based rain detection using the scribbled rain image set. Moreover, it was confirmed that the proposed method is more effective at removing rain structures from similar objects’ structures than conventional methods.

A method is proposed to estimate the concentration of pigments mixed in a painting, using the encoder–decoder model of neural networks. The model is trained to output a value that is the same as its input, and its middle output extracts a certain feature as compressed information about the input. In this instance, the input and output are spectral data of a painting. The model is trained with pigment concentration as the middle output. A dataset containing the scattering coefficient and absorption coefficient of each of 19 pigments was used. The Kubelka–Munk theory was applied to the coefficients to obtain many patterns of synthetic spectral data, which were used for training. The proposed method was tested using spectral images of 33 paintings, which showed that the method estimates, with high accuracy, the concentrations that have a similar spectrum of the target pigments.

In order to solve the issues of inadequate feature description and inefficient feature learning model existing in current classification methods, this article proposes a multi-channel joint sparse learning model for three-dimensional (3D) non-rigid object classification. First, the authors adopt a multi-level measurement of intrinsic properties to create complementary shape descriptors. Second, they build independent and informative bag of features (BoF) by embedding these shape descriptors into the visual vocabulary space. Third, a max-dependency and min-redundancy criterion is applied for optimal feature filtering on each BoF dictionary based on mutual information; meanwhile, each dictionary is learned and weighted according to its contribution to the classification task, and then a compact multi-channel joint sparse learning model is constructed. Finally, the authors train the joint sparse learning model followed by a Softmax classifier to implement efficient shape classification. The experimental results show that the proposed method has stronger feature representation ability and promotes greatly the discrimination of sparse coding coefficients. Thus, the promising classification performance and the powerful robustness can be obtained compared to the state-of-the-art methods.

The search for exoplanets is a focal topic in astronomy. Since the signal from the detected target is very weak, the imaging system needs to have ultra-low readout noise. Therefore, a low noise charge-coupled diode (CCD) imaging system for exoplanet search (LNCIS) is proposed. Based on the area array CCD (TH7888A), the circuit and timing drive of LNCIS are designed. Especially, the application of correlation dual sampling (CDS) and asynchronous first-in, first-out (FIFO) memory can effectively suppress the correlation noise of the image signal. Moreover, this article proposes a fully differential double correlation sampling method, which can achieve better sampling effect and can better eliminate common-mode noise, improve dynamic range, and achieve high-quality image signal output. In addition, an independent counting method for adjusting the exposure time is proposed, which satisfies the requirements of the long exposure time of the imaging system, so that the CCD can be provided an independent and adjustable exposure time in the photosensitive stage. The LNCIS uses the FPGA (ZYNQ7000) as the core control device to produce the timing according to the function of the system. Finally, the experimental results show that the real-time image acquisition is achieved under the condition that the CCD readout clock frequency is 20 MHz. It is verified that the circuit and timing drive of the imaging system can meet the design requirements.

Spinal surgery is of high risk due to the possibility of neurologic damage, which may cause life-threatening sequelae. Although the emerging robotic-assisted spinal surgery provides better accuracy compared with traditional surgery, the construction of boundary constraints around the spinal canal for safety in surgery is still required. The establishment of a three-dimensional (3D) model of the spinal canal during preoperative preparation can facilitate the generation of surgical boundary constraints. This article presents a novel framework for spinal canal generation based on spinal CT image inpainting by using the boundary equilibrium generative adversarial network (BEGAN). First, U-net is used to simplify the image features and then ResNet50 is applied to classify the vertebral foramen features and mark the area to be restored. Finally, BEGAN generates the target features to complete the vertebral foramina inpainting for the generation of the spinal canal. The experimental results show that the average accuracies (Mean Intersection over Union) of the vertebral foramina and spine inpainting are 0.9396 and 0.9332, respectively, and the accuracy of image inpainting decreases with increase in the inpainting area. The proposed method can accurately generate the vertebral contours and complete the 3D reconstruction of the spinal canal.

In this article, a system Smart Emergency Notification System (SENS) is proposed for both emergency responders and the community. SENS detects single/multiple emergency case(s) (i.e. road accident, fire, and injury) automatically from images sent by a smartphone via the Internet by the proposed promising approach; afterward, it notifies the police, fire brigade, and/or ambulance. The SENS has three modules: the mobile application SENSdroid, the Web application WebSENS, and the software agent NotiSENS, which uses the proposed approach. This approach is as follows. First, a dataset that contains accident, fire, and injury images was constructed; their labels were obtained for training; the trained results, Google Cloud Vision API, and cosine similarity measurement were used to detect the emergency case(s) for an input image. Based on the test results, the approach has 84% sensitivity, 92% specificity, and 88% accuracy. It is possible to say that SENS would have a positive effect on helping the harmed person, supporting the staff on duty, protecting the person who can be harmed, and/or saving Nature. Additionally, this system would have high usability because of its easy-to-use features and high rates of smartphone and Internet users. It is believed that SENS could be an efficient and useful system.