Abstract
Connected-component labeling is an important process in image analysis and pattern recognition. It aims to deduct the connected components by giving a unique label value for each individual component. Many algorithms have been proposed, but they still face several problems such as slow execution time, falling in the pipeline, requiring a huge amount of memory with high resolution, being noisy, and giving irregular images. In this work, a fast and memory- efficient connected-component labeling algorithm for binary images is proposed. The proposed algorithm is based on a new run-base tracing method with a new resolving process to find the final equivalent label values. A set of experiments were conducted on different types of binary images. The proposed algorithm showed high performance compared to the other algorithms.
Highlights
Connected-component labeling (CCL) is an essential technique in computer visions, image analysis, and pattern recognition
In [8], Klaiber et al claimed that the worst case scenario of CCL algorithms requires a huge amount of memory based on the image size
The performance of the proposed algorithm is compared with the state of the art (HCS [5], LSL ST D [9], He et al [10], HCS2 [11], Grana [12], Rosenfeld [16], and RCM [29] algorithms) based on the execution time of the first pass, the number of labels generated in the first pass, the execution time of the whole process, the stability of the performance with different benchmark images, and the memory required for buffering the provisional labels
Summary
Connected-component labeling (CCL) is an essential technique in computer visions, image analysis, and pattern recognition. Based on [9], the main objective in CCL research is to propose a faster algorithm in several computer architectures, with a minimum amount of memory used, labels created, and complexity. He et al mentioned in several works such as [5,10,11] that faster CCL algorithms are often required especially in real-time dynamic images, complicated geometric shapes, and complex connectivity applications
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
