Offline Urdu Nastaleeq text recognition has long been a serious problem due to its very cursive nature. In order to get rid of the character segmentation problems, many researchers are shifting focus towards segmentat...Offline Urdu Nastaleeq text recognition has long been a serious problem due to its very cursive nature. In order to get rid of the character segmentation problems, many researchers are shifting focus towards segmentation free ligature based recognition approaches. Majority of the prevalent ligature based recognition systems heavily rely on hand-engineered feature extraction techniques. However, such techniques are more error prone and may often lead to a loss of useful information that might hardly be captured later by any manual features. Most of the prevalent Urdu Nastaleeq test recognition was trained and tested on small sets. This paper proposes the use of stacked denoising autoencoder for automatic feature extraction directly from raw pixel values of ligature images. Such deep learning networks have not been applied for the recognition of Urdu text thus far. Different stacked denoising autoencoders have been trained on 178573 ligatures with 3732 classes from un-degraded(noise free) UPTI(Urdu Printed Text Image) data set. Subsequently, trained networks are validated and tested on degraded versions of UPTI data set. The experimental results demonstrate accuracies in range of 93% to 96% which are better than the existing Urdu OCR systems for such large dataset of ligatures.展开更多
All kinds of sensing organs in humans are able to reflect only the formal factors of objects,named formal information.It is believed,however,that not only the formal information but also the content information and va...All kinds of sensing organs in humans are able to reflect only the formal factors of objects,named formal information.It is believed,however,that not only the formal information but also the content information and value information of objects could play fundamental roles in the process of information understanding and decisionmaking in human thinking.Therefore,the questions of where and how the content information and the value information be produced from the formal information become critical in the theory of information understanding and decision-making.A conjectural theory that may reasonably answer the question is presented here in the paper.展开更多
The paper proposes a novel probabilistic generative model for simultaneous image classification and annotation. The model considers the fact that the category information can provide valuable information for image ann...The paper proposes a novel probabilistic generative model for simultaneous image classification and annotation. The model considers the fact that the category information can provide valuable information for image annotation. Once the category of an image is ascertained, the scope of annotation words can be narrowed, and the probability of generating irrelevant annotation words can be reduced. To this end, the idea that annotates images according to class is introduced in the model. Using variational methods, the approximate inference and parameters estimation algorithms of the model are derived, and efficient approximations for classifying and annotating new images are also given. The power of our model is demonstrated on two real world datasets: a 1 600-images LabelMe dataset and a 1 791-images UIUC-Sport dataset. The experiment results show that the classification performance is on par with several state-of-the-art classification models, while the annotation performance is better than that of several state-of-the-art annotation models.展开更多
基金National Natural Science Foundation of China (Project No. 61273365)111 Project (No. B08004) are gratefully acknowledged
文摘Offline Urdu Nastaleeq text recognition has long been a serious problem due to its very cursive nature. In order to get rid of the character segmentation problems, many researchers are shifting focus towards segmentation free ligature based recognition approaches. Majority of the prevalent ligature based recognition systems heavily rely on hand-engineered feature extraction techniques. However, such techniques are more error prone and may often lead to a loss of useful information that might hardly be captured later by any manual features. Most of the prevalent Urdu Nastaleeq test recognition was trained and tested on small sets. This paper proposes the use of stacked denoising autoencoder for automatic feature extraction directly from raw pixel values of ligature images. Such deep learning networks have not been applied for the recognition of Urdu text thus far. Different stacked denoising autoencoders have been trained on 178573 ligatures with 3732 classes from un-degraded(noise free) UPTI(Urdu Printed Text Image) data set. Subsequently, trained networks are validated and tested on degraded versions of UPTI data set. The experimental results demonstrate accuracies in range of 93% to 96% which are better than the existing Urdu OCR systems for such large dataset of ligatures.
基金The work was supported in part by the National Natural Science Foundation of China(Grant Nos.60575034 and 60873001)。
文摘All kinds of sensing organs in humans are able to reflect only the formal factors of objects,named formal information.It is believed,however,that not only the formal information but also the content information and value information of objects could play fundamental roles in the process of information understanding and decisionmaking in human thinking.Therefore,the questions of where and how the content information and the value information be produced from the formal information become critical in the theory of information understanding and decision-making.A conjectural theory that may reasonably answer the question is presented here in the paper.
基金supported by the Major Research Plan of the National Natural Science Foundation of China (90920006)
文摘The paper proposes a novel probabilistic generative model for simultaneous image classification and annotation. The model considers the fact that the category information can provide valuable information for image annotation. Once the category of an image is ascertained, the scope of annotation words can be narrowed, and the probability of generating irrelevant annotation words can be reduced. To this end, the idea that annotates images according to class is introduced in the model. Using variational methods, the approximate inference and parameters estimation algorithms of the model are derived, and efficient approximations for classifying and annotating new images are also given. The power of our model is demonstrated on two real world datasets: a 1 600-images LabelMe dataset and a 1 791-images UIUC-Sport dataset. The experiment results show that the classification performance is on par with several state-of-the-art classification models, while the annotation performance is better than that of several state-of-the-art annotation models.