Active appearance models (AAMs) have demonstrated great utility when being employed for non-rigid face alignment/tracking. The “simultaneous” algorithm for fitting an AAM achieves good non-rigid face registration performance, but has poor real time performance (2–3 fps). The “project-out” algorithm for fitting an AAM achieves faster than real time performance (>200 fps) but suffers from poor generic alignment performance. In this paper we introduce an extension to a discriminative method for non-rigid face registration/tracking referred to as a constrained local model (CLM). Our proposed method is able to achieve superior performance to the “simultaneous” AAM algorithm along with real time fitting speeds (35 fps). We improve upon the canonical CLM formulation, to gain this performance, in a number of ways by employing: (i) linear SVMs as patch-experts, (ii) a simplified optimization criteria, and (iii) a composite rather than additive warp update step. Most notably, our simplified optimization criteria for fitting the CLM divides the problem of finding a single complex registration/warp displacement into that of finding N simple warp displacements. From these N simple warp displacements, a single complex warp displacement is estimated using a weighted least-squares constraint. Another major advantage of this simplified optimization lends from its ability to be parallelized, a step which we also theoretically explore in this paper. We refer to our approach for fitting the CLM as the “exhaustive local search” (ELS) algorithm. Experiments were conducted on the CMU MultiPIE database.

主动外观模型（AAM）在用于非刚性面部对齐/跟踪时已表现出巨大的实用性。用于拟合 AAM 的“同时”算法实现了良好的非刚性人脸配准性能，但实时性能较差（2-3 fps）。用于拟合 AAM 的“project-out”算法实现了比实时性能更快的速度（>200 fps），但通用对齐性能较差。在本文中，我们介绍了非刚性人脸注册/跟踪的判别方法的扩展，称为约束局部模型（CLM）。我们提出的方法能够实现优于“同步”AAM 算法的性能以及实时拟合速度（35 fps）。我们改进了规范的 CLM 公式，通过采用以下多种方式获得这种性能：(i) 线性 SVM 作为补丁专家，(ii) 简化的优化标准，以及 (iii) 复合而不是附加的扭曲更新步。最值得注意的是，我们用于拟合 CLM 的简化优化标准将寻找单个复杂配准/扭曲位移的问题划分为寻找 N 个简单扭曲位移的问题。根据这 N 个简单扭曲位移，使用加权最小二乘约束来估计单个复杂扭曲位移。这种简化优化的另一个主要优势在于其并行化能力，我们也在本文中从理论上探讨了这一步骤。我们将拟合 CLM 的方法称为“详尽局部搜索”(ELS) 算法。实验在 CMU MultiPIE 数据库上进行。