Compactification of Affine Transformation Filter Using Tensor Decomposition

Compactification of Affine Transformation Filter Using Tensor Decomposition
复制标题

DOI：
10.1109/icip.2018.8451195
复制
发表时间：
2018-10
期刊：
2018 25th IEEE International Conference on Image Processing (ICIP)
影响因子：
--
通讯作者：
Kohei Kawai;Takahiro Hasegawa;Yuji Yamauchi;Takayoshi Yamashita;H. Fujiyoshi
Kohei Kawai;Takahiro Hasegawa;Yuji Yamauchi;Takayoshi Yamashita;H. Fujiyoshi
中科院分区：
其他
文献类型：
--
作者：
Kohei Kawai;Takahiro Hasegawa;Yuji Yamauchi;Takayoshi Yamashita;H. Fujiyoshi

文献摘要

相似文献

关键点匹配用于各种任务，例如特定对象识别和全景图像生成。仿射-SIFT（ASIFT）通过生成输入图像的许多仿射变换图像来实现仿射不变匹配。它描述了所生成的图像的尺度不变特征变换（SIFT）特征。然而，ASIFT必须执行多个昂贵的仿射变换的在线计算。我们表示一个定向的FAST和旋转的BRIEF（ORB）描述符在一个线性滤波器进行许多仿射变换。我们通过卷积生成的滤波器与补丁图像来计算仿射特征。然而，卷积由仿射变换生成的19，200个滤波器是低效的。为了减少卷积处理，仿射变换滤波器是紧凑的因式分解方法。我们使用仿射变换滤波器构建了一个4阶张量。4阶张量分解为Tucker模型。我们为每种模式适当地降低维度。通过这种方式，我们提出了一个紧凑和准确的特征描述。我们的评估实验证实，所提出的方法减少了19%的处理时间，同时保持相同的精度奇异值分解，这是传统的方法。
Keypoint matching is used in a variety of tasks such as specific object recognition and panoramic image generation. Affine-SIFT (ASIFT) enables affine invariant matching by generating many affine transformation images of an input image. It describes the scale-invariant feature transform (SIFT) features of the generated image. However, ASIFT must perform multiple costly online computations for affine transformation. We represent an oriented FAST and rotated BRIEF (ORB) descriptor in a linear filter subjected to many affine transformations. We calculate the affine features by convolving the generated filter with the patch image. However, convolving the 19,200 filters generated by the affine transformation is inefficient. In order to reduce the convolution processing, the affine transformation filter is made compact by a factorization method. We built a 4-order tensor using the affine transformation filter. The 4-order tensor decomposes into the Tucker model. We reduce dimensions appropriately for each mode. In this way, we propose a compact and accurate feature description. Our evaluation experiments confirmed that the proposed method reduces the processing time to 19% while maintaining the same precision as singular value decomposition, which is the conventional method.