IEEE Trans Image Process. 2018 Sep;27(9):4452-4464. doi: 10.1109/TIP.2018.2839886.
We construct a new efficient near duplicate image detection method using a hierarchical hash code learning neural network and load-balanced locality-sensitive hashing (LSH) indexing. We propose a deep constrained siamese hash coding neural network combined with deep feature learning. Our neural network is able to extract effective features for near duplicate image detection. The extracted features are used to construct a LSH-based index. We propose a load-balanced LSH method to produce load-balanced buckets in the hashing process. The load-balanced LSH significantly reduces the query time. Based on the proposed load-balanced LSH, we design an effective and feasible algorithm for near duplicate image detection. Extensive experiments on three benchmark data sets demonstrate the effectiveness of our deep siamese hash encoding network and load-balanced LSH.
我们使用分层哈希码学习神经网络和负载均衡局部敏感哈希 (LSH) 索引构建了一种新的高效近重复图像检测方法。我们提出了一种深度约束的孪生哈希编码神经网络，结合了深度特征学习。我们的神经网络能够提取有效的近重复图像检测特征。提取的特征用于构建基于 LSH 的索引。我们提出了一种负载均衡的 LSH 方法，在哈希过程中生成负载均衡的桶。负载均衡的 LSH 显著减少了查询时间。基于所提出的负载均衡 LSH，我们设计了一种用于近重复图像检测的有效且可行的算法。在三个基准数据集上的广泛实验证明了我们的深度孪生哈希编码网络和负载均衡 LSH 的有效性。
