A mixed edge based text detection method by applying image complexity analysis

With the rapid development of industries such as nuclear power and shipbuilding, radiographic testing (RT) is widely used in these fields as an important means of weld inspection. It also produces a large number of radiographic films, which consume a great deal of manpower and material resources. It is therefore beneficial for the radiographic film to be digitised for storage and archiving. Text detection in RT weld images is an important prerequisite for the archiving of digitised films. This paper proposes a novel text detection method that employs mask convolution and frequency-domain filtering, which can detect text at different positions, with different fonts and of different sizes in RT weld images. The method is evaluated using 366 different images and shows significant efficacy for text detection in RT weld images, with the precision value reaching 96%. The method used in this paper is also compared with other methods that are commonly used in other fields and the results show that the proposed method gives improved results compared to state-of-the-art methods.

We present a novel deep neural model for text detection in document images. For robust text detection in noisy scanned documents, the advantages of multi-task learning are adopted by adding an auxiliary task of text enhancement. Namely, our proposed model is designed to perform noise reduction and text region enhancement as well as text detection. Moreover, we enrich the training data for the model with synthesized document images that are fully labeled for text detection and enhancement, thus overcome the insufficiency of labeled document image data. For the effective exploitation of the synthetic and real data, the training process is separated in two phases. The first phase is training only synthetic data in a fully-supervised manner. Then real data with only detection labels are added in the second phase. The enhancement task for the real data is weakly-supervised with information from their detection labels. Our methods are demonstrated in a real document dataset with performances exceeding those of other text detection methods. Moreover, ablations are conducted and the results confirm the effectiveness of the synthetic data, auxiliary task, and weak-supervision. Whereas the existing text detection studies mostly focus on the text in scenes, our proposed method is optimized to the applications for the text in scanned documents.

The multiuser detection is a signal processing tech- nique which enhances the performance and capacity in DS- CDMA technology. Since its complexity issue was too expensive to handle, there was focus on the suboptimal detectors. In this paper we propose a hybrid method called adaptive differential interference cancellation method (ADIC) which is a hybrid of the differential interference cancellation method and which is then combined in a adaptive way to determine a weight matrix which will map the outcome of the differential interference cancellation method to come out with a better performance. This paper also looks into the computational cost of different methods using the floating point operation (flops) which is a good estimation of the comparative computational cost if not the exact one. I. INTRODUCTION The conventional DS-CDMA match filter detector fails to combat these issues due three prominent drawbacks: unrealis- tic ucorrelated code, near-far problem (even with strict power control (1)), and tough multiple access interference (MAI). Many advanced signal processing approaches have been made to improve the performances of these kinds of detectors. In this paper we will study the different approaches that were made in this field and implement these methods to reach a conclusion about the detection methods. As the name of the topic suggests the focus of our work will be study and propose cost effective better performing multiuser detection method. We will explore Multiuser Detection Techniques in Synchronous CDMA environment. Multi-user detection deals with the development and ap- plication of joint demodulation and interference cancellation cancellation techniques for improved detection of a desired set of digital signals in the presence of multiple access interfer- ence, intersymbol interference and noise. Since veterbi forward dynamic algorithm (2) is used in case of Optimum multiuser detection (3) the complexity grows in with the increase in the number of users. Hence the complexity is immense which increases exponentially with the increase in the number of users. Looking ahead for lower complexity hence lesser cost of implementation, the paper proposes the use of sub-optimal linear detectors (4). The sub-optimal detector the paper next focuses on is Decorrelator type of Detector (5) which is optimal in least squares. This detector out performs the optimal detector in many respects. Then the Minimum Mean Square Error (MMSE) linear detector is proposed which tries to minimize the squared error from the required transformation. It is one of the most popular detectors in use due to its easiness to implement and its lower complexity. But then in the above detection methods the decisions made were based on certain linear transformation criterion and there are missing efforts to check the performance in between the detection process to improvise the transformation method better detection. So then the paper proposes Adaptive multiuser detection. Then the paper focuses on Interference cancellation methods which utilize the feedback to reduce Multiple Access Interference (MAI) in the detected bits. Under the Interference Cancellation umbrella the Successive Interference Cancellation (SIC) (6), (7) method is explored and simulated to observe the results. Then the next method which performs better than SIC and more commonly used in real life, called Parallel Interference Cancellation (PIC) (6), (8) is also implemented. Before going ahead to implement the final proposed detection method, this paper implements Differential Interference Cancellation (DIC) (9) method. And then this paper finally proposes an Inter- ference Cancellation method called the Adaptive Differential Interference Cancellation Multiuser Detection method which is cost effective in comparison to other Interference Cancellation methods as we will require lesser hardware (multipliers as in the SIC or Parallel Interference Cancellation (PIC)) for that matter. More ever since we are using adaptive method the desired BER can be further reduced. This proposed method will be discussed in detail in the following section.

Text detection and recognition in scene images and videos attract much attention in computer vision recently. However, most existing text detection and recognition methods only focus on static images. In this paper an end-to-end scene text recognition method based on multi frame tracking is proposed for text in videos, in which temporal information is employed to improve performance. First, an end-to-end text recognition method based on a unified deep neural network is used to detect and recognize text in each frame of the input video. Then, multi frame text tracking is employed through associations of texts in current frame and several previous frames to obtain final results. Experiments on ICDAR datasets demonstrate that the proposed method outperforms the state-of-the-art methods in end-to-end video text recognition.

In this paper, a proposal of a new and unusual framework to detect and extract the text from the images and video frames have been presented. In the past various methods have been presented for detection and localization of text in images and video frames. In this paper, a comparison has been made between several text detection methods and proposed method for text detection in images and video frames. The proposed method is carried out by edge detection, and the projection profile method is used to localize the text region better. Various experiments have been carried out to evaluate and compare the performance of the proposed algorithm. Experimental results tested from a large dataset have demonstrated that the proposed method is effective and practical. Various parameters like average time, precision and recall rates and analyzed for both existing and proposed method to determine the success and limitation of our method.

Historical handwritten manuscripts pose challenges to automated recognition techniques due to their unique handwriting styles and cultural backgrounds. In order to solve the problems of complex text word misdetection, omission, and insufficient detection of wide-pitch curved text, this study proposes a high-precision text detection method based on improved YOLOv8s. Firstly, the Swin Transformer is used to replace C2f at the end of the backbone network to solve the shortcomings of fine-grained information loss and insufficient learning features in text word detection. Secondly, the Dysample (Dynamic Upsampling Operator) method is used to retain more detailed features of the target and overcome the shortcomings of information loss in traditional upsampling to realize the text detection task for dense targets. Then, the LSK (Large Selective Kernel) module is added to the detection head to dynamically adjust the feature extraction receptive field, which solves the cases of extreme aspect ratio words, unfocused small text, and complex shape text in text detection. Finally, in order to overcome the CIOU (Complete Intersection Over Union) loss in target box regression with unclear aspect ratio, insensitive to size change, and insufficient correlation between target coordinates, Gaussian Wasserstein Distance (GWD) is introduced to modify the regression loss to measure the similarity between the two bounding boxes in order to obtain high-quality bounding boxes. Compared with the State-of-the-Art methods, the proposed method achieves optimal performance in text detection, with the precision and mAP@0.5 reaching 86.3% and 82.4%, which are 8.1% and 6.7% higher than the original method, respectively. The advancement of each module is verified by ablation experiments. The experimental results show that the method proposed in this study can effectively realize complex text detection and provide a powerful technical means for historical manuscript reproduction.

This paper focuses on fine-grained object classification using recognized scene text in natural images. While the state-of-the-art relies on visual cues only, this paper is the first work which proposes to combine textual and visual cues. Another novelty is the textual cue extraction. Unlike the state-of-the-art text detection methods, we focus more on the background instead of text regions. Once text regions are detected, they are further processed by two methods to perform text recognition, i.e., ABBYY commercial OCR engine and a state-of-the-art character recognition algorithm. Then, to perform textual cue encoding, bi- and trigrams are formed between the recognized characters by considering the proposed spatial pairwise constraints. Finally, extracted visual and textual cues are combined for fine-grained classification. The proposed method is validated on four publicly available data sets: ICDAR03, ICDAR13, Con-Text, and Flickr-logo. We improve the state-of-the-art end-to-end character recognition by a large margin of 15% on ICDAR03. We show that textual cues are useful in addition to visual cues for fine-grained classification. We show that textual cues are also useful for logo retrieval. Adding textual cues outperforms visual- and textual-only in fine-grained classification (70.7% to 60.3%) and logo retrieval (57.4% to 54.8%).

Developing assisting system of handicapped persons become a challenging ask in research projects. Recently, a variety of tools are designed to help visually impaired or blind people object as a visual substitution system. The majority of these tools are based on the conversion of input information into auditory or tactile sensory information. Furthermore, object recognition and text retrieval are exploited in the visual substitution systems. Text detection and recognition provides the description of the surrounding environments, so that the blind person can readily recognize the scene. In this work, we aim to introduce a method for detecting and recognizing text in indoor scene. The process consists on the detection of the regions of interest that should contain the text using the connected component. Then, the text detection is provided by employing the images correlation. This component of an assistive blind person should be simple, so that the users are able to obtain the most informative feedback within the shortest time.

Forensic watermarking is used in large-scale video-distribution applications to track digital pirates after they illegally leak videos. Existing methods either have a high embedding complexity or have troubles providing imperceptibility and robustness. Therefore, this paper proposes a novel watermarking method that has a low embedding complexity, as well as sufficient imperceptibility and robustness. The main novelty is that frames are replaced out of the loop, which has a very low complexity. This is inspired by A/B watermarking, yet applied on frame level rather than video-segment level. The resulting drift-error artifacts are used for robust watermark detection. Additionally, a faster watermark detection method is proposed at the cost of a decrease in embedding capacity. We show that the drift errors caused by frame replacement are imperceptible, and that our method has a negligible impact on the video bitrate. Moreover, we demonstrate a high level of robustness. These interesting properties come at the cost of a non-blind detection with a relatively high complexity, that is partially solved by the proposed fast detection method. Additionally, a high detection complexity is not necessarily a problem since detection occurs infrequently and recent speed-up solutions exist. In conclusion, the proposed method is a novel and scalable solution that enables secure large-scale video distribution.

A method of text detection in natural images, to be turned into an effective embedded software on a mobile device, shall be both efficient and lightweight. We observed that a simple method based on the morphological Laplace operator is very appropriate: we can construct in quasi-linear time a hierarchical image decomposition/simplification based on its 0-crossings, and search for some text in the resulting tree. Yet, for this decomposition to be sound, we need “0-crossings” to be Jordan curves, and to that aim, we rely on some discrete topology tools. Eventually, the hierarchical representation is the morphological tree of shapes of the Laplacian sign (ToSL). Moreover, we provide an algorithm with linear time complexity to compute this representation. We expect that the proposed hierarchical representation can be useful in some applications other than text detection.

For improving the processing speed and accuracy of edge detection, an adaptive edge detection method based on improved NMS (nonmaximum suppression) was proposed in this paper. In the method, the gradient image was computed by four directional Sobel operators. Then, the gradient image was processed by using NMS method. By defining a power map function, the elements values of gradient image histogram were mapped into a wider value range. By calculating the maximal between-class variance according to the mapped histogram, the corresponding threshold was obtained as adaptive threshold value in edge detection. Finally, to be convenient for engineering application, the proposed method was realized in FPGA (Field Programmable Gate Array). The experiment results demonstrated that the proposed method was effective in edge detection and suitable for real-time application.

In this paper, we propose a new method for natural image text detection under a weakly supervised data set. Currently, most of the text detection models are based on bounding box label training data. However, the cost of the bounding box label training data is very high. In order to solve this problem, we propose an attention mechanism that can be trained on image-level labels data and roughly identifies text regions via an automatically learned attentional map based on a convolutional neural network. There are three main steps: firstly, a VGG model is trained using image-level labels data to score the likelihood that a text region exists in the picture; secondly, the region of interest is extracted by means of the attention mechanism and the extracted region is evaluated using the network trained in the first step to getting the text region and finally, the text line is extracted in the text region using the MSER algorithm. Trained with the weakly supervised data which is only with image-level labels, our model can generate bounding boxes for the text line in the image. The results of our model are very close to those of the models using bounding box label training data on the text detection benchmark sets of MSRA-TD500, ICDAR2013, and ICDAR2015.

Due to the large variety of video type collections, it becomes difficult to achieve good text detection and recognition accuracy. We propose a new fuzzy-mass based method for classifying (categorizing) text frames from different types of video. For each frame of a video type, we formulate Fuzzy logic to identify straight and curved edge components from edge images. We then estimate mass locally and globally by drawing consecutive ellipses over edge images with respect to straight and curved edge components. Further, we extract features based on spatial proximity between centroid of classified straight/curved edge components and that of the whole image. This results local features. Next, the features are extracted for the whole image without ellipse drawing, which results in global features. The combination of both local and global features is then fed to an SVM classifier for video type classification. Experimental results on the proposed and existing classification methods show that the proposed classification outperforms the stat of art methods. Furthermore, experiments on before and after classification with several text detection and binarization methods show that the proposed classification is significant in improving text detection and recognition performance.

With the development of deep learning, the use of neural network for text detection has been more in-depth research and more widely used. Based on this, this paper studies the Chinese text event detection technology based on improved neural network. In the research, this paper uses the flower pollination algorithm (FPA) to improve the traditional BP neural network algorithm. By optimizing the weights and thresholds of BP neural network, a Chinese text event detection method based on improved neural network is proposed. In order to verify the effect of the Chinese text event detection method based on improved neural network, this paper compares it with the natural scene text detection method, and compares the recall rate, accuracy rate and time-consuming. The results show that the accuracy rate of the natural scene text detection method is 88%, and the recall rate is 73%. The accuracy rate of the text detection method based on the improved neural network is 95% and the recall rate is 86%. The F value of the natural scene text detection method in the Chinese text event detection test is 0.79, which takes 4.56s The value of F in is 0.90, which takes 0.64s. Therefore, the Chinese text event detection method based on improved neural network has better performance.

The non-maximum suppression (NMS) algorithm, which merges neighboring bounding boxes as the detection result, is widely utilized in object detection methods. However, the traditional NMS algorithm is not suitable for text detection in natural scenes, especially for long texts and dense texts. In this paper, we observe that the coordinates of candidate bounding boxes are presented in skew distribution. On this observation, an improved NMS algorithm called SD-NMS (Skew Distribution NMS) is designed. First, the mode and the median of the coordinate set are counted to filter out the redundant bounding boxes. Then the left bounding boxes are merged for the location of the text regions. The SD-NMS method improves the detection ability of the model without extra model training and can be easily embedded in text detection methods. The experimental results show that our method obtains F-measure more than other NMS methods in public data sets ICDAR2015 and MSRATD500.