关键词: 直方图凹度分析, 分段阈值, 修正因子, 自适应分割

Abstract: Under complex industrial conditions, two-dimensional DPM barcode captured by a CCD camera easily has large spots or shadow areas owing to the complex illumination. This phenomenon results in the missing information in DPM area and the identification difficulty. Therefore, this paper proposes adaptive multi-threshold segmentation algorithm based on subsection histogram concavity analysis. Firstly, on the basis of smoothed histogram, a series of local peak values are calculated by the simplified formula. Moreover, the histogram is segmented through these local peak values. Then subsection thresholds are computed by recursive algorithm. Secondly, an adaptive correction factor based on the local area information is introduced to modify the subsection threshold for the status of the low local contrast. Experimental results show that the proposed method has superior division performance and more efficient operation to traditional threshold segmentation algorithms. The average running efficiency of this method improves 17.75 times than the fastest one of those conventional algorithms. After the adaptive multi-threshold segmentation, the contrast of uneven illumination area is significantly enhanced and missing DPM regional information is effectively compensated. Therefore, the method in this paper provides a sufficient condition for the accurate identification of the DPM barcode. It can also be applied to the contrast changeable image enhancement.

Key words: histogram concavity analysis, subsection thresholds, correction factor, adaptive segmentation