Method and device for quantizing local features of picture into visual vocabularies

Abstract

The invention provides a method and device for quantizing local features of a picture into visual vocabularies, wherein the method comprises the steps of S1, deciding to-be-selected vocabularies from a first layer of a visual vocabulary tree; S2, computing the confidence degree of a route in which each to-be-selected vocabulary in the current layer exists respectively by utilizing the distance between the local feature and each to-be-selected vocabulary in the current layer and the confidence degree of a route in which a father node of each to-be-selected vocabulary in the current layer exists; and S3, selecting the to-be-selected vocabularies in the route of which the confidence degree is more than or equal to a predetermined confidence degree threshold value in the current layer and judging whether the current layer is the last layer or not, wherein if the current layer is the last layer, the vocabularies selected in the current layer are determined as the visual vocabularies of the local features; and if the current layer is not the last layer, the vocabularies selected from the current layer enter the next layer, child nodes of the selected vocabularies are determined as the to-be-selected vocabulary in the next layer and the operation returns to the step S2. With the adoption of the method and device for quantizing the local features of the picture into the visual vocabularies, based on the improvement of the robustness of quantization errors, the computation overhead during the quantization process is decreased.

Description

【Technical field】 [0001] The invention relates to the technical field of computer applications, in particular to a method and device for quantifying local features of pictures into visual words. 【Background technique】 [0002] With the development of multimedia-related technologies, the scale of digital pictures is rapidly expanding, and its applications are becoming more and more extensive. Therefore, how to effectively and quickly retrieve the required pictures from large-scale picture data has become a research hotspot. Due to the disadvantages of subjectivity and uncertainty caused by manual annotation of pictures, the traditional text-based image retrieval method can no longer meet the user's query requirements. Therefore, content-based image retrieval technology has gradually emerged and been widely used. [0003] Establishing an inverted index for pictures based on visual vocabulary is a general content-based image retrieval method. This method first determines the lo...

AI Technical Summary

Problems solved by technology

[0006] The above-mentioned closest path mapping method is easy to cause quantization errors because each layer selects a nearest vocabulary, and small changes in the local features of the picture are also easily quantized to different visual vocabulary, resulting in mismatching and poor robustness.

Although the greedy N-adjacent path mapping method enhances the robustness to quantization errors, N words are selected for each layer of comparison, that is, each layer needs to enter N paths, which brings a large computational overhead

Images