Title :
Memory-Efficient Architecture for Hysteresis Thresholding and Object Feature Extraction
Author :
Najjar, Mayssaa A. ; Karlapudi, Swetha ; Bayoumi, Magdy A.
Author_Institution :
Center for Adv. Comput. Studies, Univ. of Louisiana at Lafayette, Lafayette, LA, USA
Abstract :
Hysteresis thresholding is a method that offers enhanced object detection. Due to its recursive nature, it is time consuming and requires a lot of memory resources. This makes it avoided in streaming processors with limited memory. We propose two versions of a memory-efficient and fast architecture for hysteresis thresholding: a high-accuracy pixel-based architecture and a faster block-based one at the expense of some loss in the accuracy. Both designs couple thresholding with connected component analysis and feature extraction in a single pass over the image. Unlike queue-based techniques, the proposed scheme treats candidate pixels almost as foreground until objects complete; a decision is then made to keep or discard these pixels. This allows processing on the fly, thus avoiding additional passes for handling candidate pixels and extracting object features. Moreover, labels are reused so only one row of compact labels is buffered. Both architectures are implemented in MATLAB and VHDL. Simulation results on a set of real and synthetic images show that the execution speed can attain an average increase up to for the pixel-based and for the block-based when compared to state-of-the-art techniques. The memory requirements are also drastically reduced by about 99%.
Keywords :
decision making; feature extraction; hardware description languages; image segmentation; memory architecture; object detection; MATLAB; VHDL; connected component analysis; decision making; high-accuracy pixel-based architecture; hysteresis thresholding; memory requirement; memory resource; memory-efficient architecture; object detection; object feature extraction; queue-based technique; real image; streaming processor; synthetic image; Accuracy; Feature extraction; Hysteresis; Memory management; Object detection; Component labeling; feature extraction; hysteresis thresholding; streaming processors;
Journal_Title :
Image Processing, IEEE Transactions on
DOI :
10.1109/TIP.2011.2147324