使用动态图像处理技术和遗传算法的车牌定位算法-2014.pdfVIP

244 IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, VOL. 18, NO. 2, APRIL 2014 Localization of License Plate Number Using Dynamic Image Processing Techniques and Genetic Algorithms G. Abo Samra and F. Khalefah Abstract —In this research, the design of a new genetic al- specific plates having fixed colors [2]–[4]. External-shape- gorithm (GA) is introduced to detect the locations of license based techniques were developed to detect the plate based on plate (LP) symbols. An adaptive threshold method is applied to its rectangular shape [5]–[8]. Edge-based techniques were also overcome the dynamic changes of illumination conditions when converting the image into binary. Connected component analysis implemented to detect the plate based on the high density of technique (CCAT) is used to detect candidate objects inside vertical edges inside it [9]–[11]. Research in [12] and [13] the unknown image. A scale-invariant geometric relationship was based on the intensity distribution in the plate’s area with matrix is introduced to model the layout of symbols in any respect to its neighborhood where the plate is considered maxi- LP that simplifies system adaptability when applied in different mally stable extremal region. Many researchers have combined countries. Moreover, two new crossover operators, based on sorting, are introduced, which greatly improve the convergence different features in their systems [14]–[18]. The applied speed of the system. Most of the CCAT problems, such as detection algorithms ranged from