中文摘要：

针对传统外极线约束的匹配算法存在误匹配率、漏匹配率较高的问题，提出了基于图像相似几何特征的双目匹配检验和筛选算法。利用外极线几何约束算法获得不共外极线和共外极线的初始匹配点。根据左右图像正确的匹配点具有相似的几何位置关系，引出最大向量角和最大角度差准则。对于不共外极线的初始匹配点，提出了基于更新策略的视差梯度约束与最大向量角准则相结合的误匹配剔除算法，降低了误匹配率，并且克服了只用视差梯度约束过多误剔除的缺陷。对于共外极线的初始匹配点，提出利用最大角度差和最大向量角准则筛选正确的匹配点，然后进一步利用顺序一致性约束和视差梯度约束检验筛选的匹配点，降低了漏匹配率。实验结果表明，该算法匹配准确率高，通用性强，误匹配率和漏匹配率分别能控制在0．1％和7％以内，适用于不同复杂程度的被测物体。

英文摘要：

Concerning the high probability of mismatching and matching-loss that exists in traditional epipolar constraint matching algorithm, an algorithm based on similar image geometric features is proposed for binocular matching. The initial matching points which locate in the same or different epipolar lines are identified respectively using epipo]ar geometric constraint algorithm. According to the position similarity of matching points, maximum vector angle criterion and maximum angle difference criterion are derived. In order to match the points locat in different epipolar lines, utilizing disparity gradient limited constraint as well as maximum vector angle criterion, a mismatching elimination algorithm based on updating strategy is proposed, which can reduce the rate of mismatching and erroneous elimination. For the initial matching points locating in the same epipolar line, maximum angle difference and maximum vector angle criterion are used to extract candidate matching points. These candidate matching points are further examined, thus decreases the rate of matching-loss. Experimental results indicate that the algorithm has high matching accuracy and versatility. The incidence rate of mismatching and matching-loss can be controlled within 0.1% and 7 %, respectively, and the algorithm is appropriate for objects with different structural complexity.