Smartphones are enabling new ways of capture,hence arises the need for seamless and reliable acquisition anddigitization of documents. The quality assessment step is animportant part of both the acquisition and the digitizationprocesses. Assessing document quality could aid users during thecapture process or help improve image enhancement methodsafter a document has been captured. Current state-of-the-artworks lack databases in the field of document image qualityassessment. In order to provide a baseline benchmark for qualityassessment methods for mobile captured documents, we presentin this paper a dataset for quality assessment that contains bothsingly- and multiply-distorted document images.The proposed dataset could be used for benchmarking qualityassessment methods by the objective measure of OCR accuracy,and could be also used to benchmark quality enhancementmethods. There are three types of documents in the dataset:modern documents, old administrative letters and receipts. Thedocument images of the dataset are captured under varyingcapture conditions (light, different types of blur and perspectiveangles). This causes geometric and photometric distortions thathinder the OCR process. The ground truth of the datasetimages consists of the text transcriptions of the documents,the OCR results of the captured documents and the values ofthe different capture parameters used for each image. We alsopresent how the dataset could be used for evaluation in thefield of no-reference quality assessment. The dataset is freelyand publicly available for use by the research community athttp://navidomass.univ-lr.fr/SmartDoc-QA.

EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000065 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000065 | SxmlIndent | more

{{Explor lien
   |wiki=    Ticri/CIDE
   |area=    OcrV1
   |flux=    Main
   |étape=   Exploration
   |type=    RBID
   |clé=     Hal:hal-01319900
   |texte=   SmartDoc-QA: A Dataset for Quality Assessment of Smartphone Captured Document Images - Single and Multiple Distortions
}}