Word spotting is to make searchable unindexed image documents by locating word/words in a document image, given a query word. This problem is challenging, mainly due to the large number of word classes with very small inter-class and substantial intra-class distances. In this paper, a segmentation-based word spotting method is presented for multi-writer Persian handwritten documents using attribute-based classification and label-embedding. For this purpose, a hierarchical
framework is proposed, in which at first, the candidate are selected based on connected components(CCs) sequence. Then, the query word is segmented to constructor CCs, and similar CCs count in the candidate region of document are selected based on their distances to the CCs count of the query word. As a result, the candidate regions are extracted. In the final phase, the query word is located only in the candidate regions of the document. A well known Persian handwritten text dataset, namely FTH, is chosen as a benchmark for the presented method. The results shows that the proposed method outperforms the state-of-the-art methods, 81.02 percent for unseen word class retrieval.