Search

With the continuous development of artificial intelligence technology and the exponential growth in the number of images, image detection and recognition technology is becoming more widely used. Image knowledge management is extremely urgent. The data source of a knowledge graph is not only the text and structured data but also the visual or auditory data such as images, video, and audio. How to use multimodal information to build an information management platform is a difficult problem. In this paper, a method is proposed to construct the result of image recognition as a knowledge graph. First of all, based on the improvement in the BlendMASK algorithm, the hollow convolution kernel is added. Secondly, the effect of image recognition and the relationships between all kinds of information are analyzed. Finally, the image knowledge graph is constructed by using the relationship between the image entities. The contributions of this paper are as follows. (1) The hollow convolution kernel is added to reduce the loss from extracting feature information from high-level feature images. (2) In this paper, a method is proposed to determine the relationship between entities by dividing the recognition results of entities in an image with a threshold, which makes it possible for the relationships between images to be interconnected. The experimental results show that this method improves the accuracy and F1 value of the image recognition algorithm. At the same time, the method achieves integrity in the construction of a multimodal knowledge graph. [ABSTRACT FROM AUTHOR]

Perovskite light-emitting diodes (PeLEDs) provide excellent opportunities for low-cost, color-saturated, and large-area displays. However, the performance of blue PeLEDs lags far behind that of their green and red counterparts. Here, we show that the external quantum efficiencies (EQEs) of blue PeLEDs scale linearly with the photoluminescence quantum yields (PL QYs) of CsPb(Br x Cl 1- x ) 3 nanocrystals emitting at 460 to 480 nm. The recombination efficiency of carriers is highly sensitive to the chlorine content and the related deep-level defects in nanocrystals, causing notable EQE drops even with minor increases in chlorine defects. Minor adjustments of chlorine content through rubidium compensation on the A-site effectively suppress the formation of nonradiative defects, improving PL QYs while retaining desirable bandgaps for blue-emitting nanocrystals. Our PeLEDs with record-high efficiencies span the blue spectrum, achieving peak EQEs of 12.0% (460 nm), 16.7% (465 nm), 21.3% (470 nm), 24.3% (475 nm), and 26.4% (480 nm). This work exemplifies chlorine-defect control as a key design principle for high-efficiency blue PeLEDs.