Pre-Processing Filter Reflecting Human Visual Perception to Improve Saliency Detection Performance

Salient object detection is a method of finding an object within an image that a person determines to be important and is expected to focus on. Various features are used to compute the visual saliency, and in general, the color and luminance of the scene are widely used among the spatial features. However, humans perceive the same color and luminance differently depending on the influence of the surrounding environment. As the human visual system (HVS) operates through a very complex mechanism, both neurobiological and psychological aspects must be considered for the accurate detection of salient objects. To reflect this characteristic in the saliency detection process, we have proposed two pre-processing methods to apply to the input image. First, we applied a bilateral filter to improve the segmentation results by smoothing the image so that only the overall context of the image remains while preserving the important borders of the image. Second, although the amount of light is the same, it can be perceived with a difference in the brightness owing to the influence of the surrounding environment. Therefore, we applied oriented difference-of-Gaussians (ODOG) and locally normalized ODOG (LODOG) filters that adjust the input image by predicting the brightness as perceived by humans. Experiments on five public benchmark datasets for which ground truth exists show that our proposed method further improves the performance of previous state-of-the-art methods.

Population receptive fields of human primary visual cortex organised as DC-balanced bandpass filters

The response to visual stimulation of population receptive fields (pRF) in the human visual cortex has been modelled with a Difference of Gaussians model, yet many aspects of their organisation remain poorly understood. Here, we examined the mathematical basis and signal-processing properties of this model and argue that the DC-balanced Difference of Gaussians (DoG) holds a number of advantages over a DC-biased DoG. Through functional magnetic resonance imaging (fMRI) pRF mapping, we compared performance of DC-balanced and DC-biased models in human primary visual cortex and found that when model complexity is taken into account, the DC-balanced model is preferred. Finally, we present evidence indicating that the BOLD signal DC offset contains information related to the processing of visual stimuli. Taken together, the results indicate that V1 pRFs are at least frequently organised in the exact constellation that allows them to function as bandpass filters, which makes the separation of stimulus contrast and luminance possible. We further speculate that if the DoG models stimulus contrast, the DC offset may reflect stimulus luminance. These findings suggest that it may be possible to separate contrast and luminance processing in fMRI experiments and this could lead to new insights on the haemodynamic response.

Processing Algorithm of Irregular Table Image in Tobacco Package Based on Dual-coding Difference of Gaussians Method

Objectives: Currently, in a large number of print-out report documents from tobacco package, there exist irregular phenomena such as discontinuous vertical lines, misplaced frame lines and multi-page tables. Thus, the existing table recognition algorithm cannot be adopted to perform digital identification. In order to solve this problem, this paper proposes a table image processing algorithm based on the dual-coding difference of Gaussians iterative clustering. Firstly, the method of local regional sub-block is used to the skew correction threshold to conduct image correction. Secondly, the corrected images are coded by rows and columns, and 2D image features are transformed into 1D image features. Thirdly, the Gaussian differenced operation is adopted to obtain effective characteristic matrices that are stable and easily distinguishable. Then the iterative clustering analysis is performed to obtain the feature values of effective frame lines. Fourthly, after finishing the tasks, such as the table positioning, inner structure reconstruction, and text information identification, the dichotomy judgmentsof the integrity of multi-page tablesare realized according to the local pixel features. Finally, the text information inside the local regions and the reconstructed regions are merged, and the digital reproduction of the multi-page tables is realized. To validate the effectiveness of the proposed algorithm, an experiment in the sample set containing 12,840 table images with different resolutionsis carried out. The average detection accuracies of table positioning, table cell reconstructionand multi-page incompleteness are 98.95%, 99.80%, and 95.85%, respectively. The experimental results show that the proposed algorithm is simple and effective, and can accomplish the digital reproduction of irregular tables.

Gaussian Image Binarization

Line drawing and screentoning are two distinct areas of study in non-photorealistic rendering, where the former emphasizes object contours, while the latter conveys tone and shading information on object surfaces. As these two problems are concerned with different yet equally important features, either method seldom delivers a complete description of the scene when used alone. Yet, research community has largely treated them as separate problems and thus resulted in two entirely different sets of solutions, complicating both implementation and usage. In this paper, we present a stylistic image binarization method called hybrid difference of Gaussians (HDoG) that performs both line drawing and screentoning in a unified framework. Our method is based upon two different extensions of DoG operator: one for line extraction, and the other for tone description. In particular, we propose an extension called adaptive DoG, that uses luminance as weight to automatically generate screentone that adapts to the local tone. Experimental results demonstrate that our hybrid method effectively generates aesthetically pleasing image binarizations that encompass both line drawing and screentoning, closely resembling professional pen-and-ink illustrations. Also, being based on Gaussian filtering, our method is very fast and also easy to implement.

Spatial receptive field structure of double-opponent cells in macaque V1

The spatial processing of color is important for visual perception. Double-opponent (DO) cells likely contribute to this processing by virtue of their spatially opponent and cone-opponent receptive fields (RFs). However, the representation of visual features by DO cells in the primary visual cortex of primates is unclear because the spatial structure of their RFs has not been fully characterized. To fill this gap, we mapped the RFs of DO cells in awake macaques with colorful, dynamic white noise patterns. The spatial RF of each neuron was fitted with a Gabor function and three versions of the Difference of Gaussians (DoG) function. The Gabor function provided the more accurate description for most DO cells, a result that is incompatible with the traditionally assumed center-surround RF organization. A non-concentric version of the DoG function, in which the RFs have a circular center and a crescent-shaped surround, performed nearly as well as the Gabor model thus reconciling results from previous reports. For comparison, we also measured the RFs of simple cells. We found that the superiority of the Gabor fits over DoG fits was slightly more decisive for simple cells than for DO cells. The implications of these results on biological image processing and visual perception are discussed.

Automatic Colorization of Anime Style Illustrations Using a Two-Stage Generator

Line-arts are used in many ways in the media industry. However, line-art colorization is tedious, labor-intensive, and time consuming. For such reasons, a Generative Adversarial Network (GAN)-based image-to-image colorization method has received much attention because of its promising results. In this paper, we propose to use color a point hinting method with two GAN-based generators used for enhancing the image quality. To improve the coloring performance of drawing with various line styles, generator takes account of the loss of the line-art. We propose a Line Detection Model (LDM) which is used in measuring line loss. LDM is a method of extracting line from a color image. We also propose histogram equalizer in the input line-art to generalize the distribution of line styles. This approach allows the generalization of the distribution of line style without increasing the complexity of inference stage. In addition, we propose seven segment hint pointing constraints to evaluate the colorization performance of the model with Fréchet Inception Distance (FID) score. We present visual and qualitative evaluations of the proposed methods. The result shows that using histogram equalization and LDM enabled line loss exhibits the best result. The Base model with XDoG (eXtended Difference-Of-Gaussians)generated line-art with and without color hints exhibits FID for colorized images score of 35.83 and 44.70, respectively, whereas the proposed model in the same scenario exhibits 32.16 and 39.77, respectively.

Determination of Firebrand Characteristics Using Thermal Videos

Burning firebrands generated by wildland or prescribed fires may lead to the initiation of spot fires and fire escapes. At the present time, there are no methods that provide information on the thermal characteristics and number of such firebrands with high spatial and temporal resolution. A number of algorithms have been developed to detect and track firebrands in field conditions in our previous study; however, each holds particular disadvantages. This work is devoted to the development of new algorithms and their testing and, as such, several laboratory experiments were conducted. Wood pellets, bark, and twigs of pine were used to generate firebrands. An infrared camera (JADE J530SB) was used to obtain the necessary thermal video files. The thermograms were then processed to create an annotated IR video database that was used to test both the detector and the tracker. Following these studies, the analysis showed that the Difference of Gaussians detection algorithm and the Hungarian tracking algorithm upheld the highest level of accuracy and were the easiest to implement. The study also indicated that further development of detection and tracking algorithms using the current approach will not significantly improve their accuracy. As such, convolutional neural networks hold high potential to be used as an alternative approach.