Description: LED字符分割和识别，
在此项目中我们主要完成了对拍摄到的6位LED数字进行分割和识别的课题。识别的数字范围在0~9。由于拍摄环境比较复杂，需要解决复杂背景下对LED字符的分割问题。我们利用了图像的色彩信息，先进行基于色彩的分割，然后对分割结果进行了固定阈值的二值化，并利用投影修正完成了对LED数码管图像的分割，并使用基于模板匹配的算法进行了识别，在匹配过程中对图像进行了尺寸归一化处理。最终得到了较好的识别效果，对10幅样图的识别率达到100％-LED character segmentation and recognition, in this major project, we completed the shooting of the six LED figures for the segmentation and identification issues. Recognition of the range between 0 and 9. As the filming environment more complex, the need to address complex background of the character LED division. We took advantage of the color image information, the first color-based segmentation, and then divided the results of a fixed threshold value of the two values, and to use the projector that completed a pair of LED digital image segmentation possession, and use based on template matching algorithm for the identification, in the process of matching the right image In one size treatment. Finally a better identification effect of 10 samples the recognition rate of 100% Platform: |
Size: 11673 |
Author:yinxun |
Hits:
Description: humanface detection,the programme can be used to detect human faces from the complex background!-humanface detection, the program can be used to detect human faces f rom the complex background! Platform: |
Size: 849 |
Author:zhangwei |
Hits:
Description: 一个复杂背景下的人脸识别程序，希望大家下载，很有用的哦-a complex background of face recognition procedures in the hope that you downloaded very useful oh Platform: |
Size: 118781 |
Author:陈聪 |
Hits:
Description: 这是一个在复杂背景下，对目标圆孔的检测，但是它的背景相对比较特殊-This is a complex background, the right of the hole target detection, but its relatively unique background Platform: |
Size: 1730 |
Author:陈乔 |
Hits:
Description: 此程序是关于形态学重构，主要是为了复杂背景条件下的图像分割-this procedure on morphological remodeling is mainly to the conditions under complex background image segmentation Platform: |
Size: 1059 |
Author:li mingxi |
Hits:
Description: 自己的flash作品，静态的图形渲染，虽然不够精致，不过可作为复杂背景制作的参考。-the flash works, static graphics rendering, though not the fine, but as a complex background produced by the reference. Platform: |
Size: 19429 |
Author:相传 |
Hits:
Description: humanface detection,the programme can be used to detect human faces from the complex background!-humanface detection, the program can be used to detect human faces f rom the complex background! Platform: |
Size: 1024 |
Author:zhangwei |
Hits:
Description: 一个复杂背景下的人脸识别程序，希望大家下载，很有用的哦-a complex background of face recognition procedures in the hope that you downloaded very useful oh Platform: |
Size: 118784 |
Author:陈聪 |
Hits:
Description: 形态学重构-主要是为了复杂背景条件下的图像分割，采用matlab语言编写，具有很高的参考价值。-Morphological Reconstruction- mainly to under complex background image segmentation, using matlab language, with a high reference value. Platform: |
Size: 1024 |
Author:cwb |
Hits:
Description: 基于复杂背景，单运动目标的检测，原始混合高斯模型背景更新与检测-Based on complex background, a single moving target detection, the background of the original Gaussian mixture model updated with the detection Platform: |
Size: 283648 |
Author:aiyan |
Hits:
Description: 大名鼎鼎的方帅的博士学位论文---目前,计算机智能视频监控在理论和应用上都面临着很多难题,国内外大批学者投身于该领域的研究和探索,并且取得了大量的成果.本文是在这些成果的基础上,对计算机智能视频监控系统的关键技术进行研究.主要贡献可概括如下:首先,对目标检测技术进行了研究,并提出了一种基于背景建模的运动目标检测算法.利用统计的方法建立了基于颜色和颜色梯度的背景模型,并实时地对背景模型进行更新,最后将这两种背景模型综合考虑对目标进行了有效的检测.接着,研究了复杂背景下多目标跟踪问题,提出了基于蒙特卡罗粒子滤波器的复杂背景下多目标跟踪算法.然后,提出了目标分类算法.用有向无环图的多类支持向量机对目标进行分类,该分类器使用少量的样本,就可以得到较好的分类精度.最后,针对视频监控中的行为理解进行了探讨性的研究.建立一个行为理解的系统,这个系统由场景模型、行为模型和行为自动识别三部分组成.
-At present, the computer intelligence video frequency monitoring is facing many difficult problems in the theory and the application, the domestic and foreign large quantities of scholars join in this domain research and the exploration, and has made the massive progresses. This article is in these achievement foundation, conducts the research to the computer intelligence video frequency supervisory system s key technologies. The main contribution may summarize as follows: First, has conducted the research to the object detection technology, and proposed one kind based on the background modelling movement object detection algorithm. Has established using the statistical method based on the color and the color gradient background model, and real-time carries on the renewal to the background model, finally has carried on these two kind of background model overall evaluation to the goal the effective examination. Then, has studied under the complex background the multi-objective track que Platform: |
Size: 5263360 |
Author:王一 |
Hits:
Description: 适用于复杂背景下的差减法！效果还行！是一个难得的程序，与大家分享哈！-For complex background by subtraction! The results were OK!Is a unique program to share with you! Platform: |
Size: 2048 |
Author:师洪德 |
Hits:
Description: 提出了一种针对复杂环境下的过人脸检测方法，首先在CbCgCr空间利用直接最小二乘法构建了对光照和复杂背景鲁棒性更好肤色聚类模型，实现了准确的肤色检测；然后针对人脸中姿态和表情变化，提出了基于Adaboost的多姿态人脸检测，精确的实现了人脸检测定位。-Extraordinary face detection method for complex environments, the first space CbCgCr direct least squares method to build a better robustness to light and complex background color clustering model to achieve accurate color detection forface, posture and facial expression changes, proposed the multi-pose face detection based on Adaboost, accurate face detection and location.
Platform: |
Size: 5086208 |
Author:洁洁 |
Hits:
Description: 利用背景抑制实现复杂背景下的小目标检测，具有一定的实用性。-This program realizes small target detection under complex background by background suppression , and it possesses a certain practically Platform: |
Size: 4096 |
Author:Lvjianming |
Hits:
Description: 提出了一种基于模型切换的背景建模方法(M SBM ).该方法以嫡图像为纽带, 实现了不同精细程度的背景模型在空间上的自适应选取和在时间上的自适应切换.对于亮度分布复杂度高的背景区域采用精细的模型以保证运动目标检测的精度,反之采用简单的模型以降低计算量
.通过模型结构自适应结合参数自适应, 很好地兼顾了检测精度和计算代价.墓于高斯混合模型和时间平均模型的双模型切换式运动目标检测算法被用于实验研究, 结果表明这种算法的检测效果和单独采用高斯混合模型的检测效果相当, 而计算速度却比后者提高很多-Proposed a model of background modeling method switching (M SBM) Based on the method of entropy image as a link, to achieve different degrees of background model in the fine spatial adaptive selection and adaptive switching in time. For high brightness distribution complex background area using sophisticated models to ensure the accuracy of the moving target detection, whereas a simple model to reduce the amount of computation
By combining adaptive parameter adaptive model structure, a good balance between detection accuracy and computational cost dual model tomb on Gaussian mixture model and the time-averaged model switched moving target detection algorithm is used for experimental research results show that the detection algorithm using Gaussian mixture model and a separate testing results have been very, and improve computing speed than many of the latter Platform: |
Size: 851968 |
Author: |
Hits:
Description: 关于复杂背景下空中目标红外图像仿真方面的一篇硕士论文-On air targets under complex background infrared image simulation aspects of a master' s thesis Platform: |
Size: 1713152 |
Author:chen |
Hits:
Description: 随着红外成像技术的发展，红外小目标检测在军事领域有越来越重要的应用。以此为背景，研究了天空、海面、大地等各种背景下红外视频中弱小目标的检测问题。
-With the development of infrared technology,dim small targets detection play a
more and more important part in the military. The problem of dim small targets
detecting in a infrared video with the background of the sky,the sea and the groundhas been studied.
Platform: |
Size: 3824640 |
Author:周文涛 |
Hits:
Search - COMPLEX BACKGROUND