Handwritten Text Generation (HTG) conditioned on text and style is a challenging task due to the variability of inter-user characteristics and the unlimited combinations of characters that form new words unseen during training. Diffusion Models have recently shown promising results in HTG but still remain under-explored. We present DiffusionPen (DiffPen), a 5-shot style handwritten text generation approach based on Latent Diffusion Models. By utilizing a hybrid style extractor that combines metric learning and classification, our approach manages to capture both textual and stylistic characteristics of seen and unseen words and styles, generating realistic handwritten samples. Moreover, we explore several variation strategies of the data with multi-style mixtures and noisy embeddings, enhancing the robustness and diversity of the generated data. Extensive experiments using IAM offline handwriting database show that our method outperforms existing methods qualitatively and quantitatively, and its additional generated data can improve the performance of Handwriting Text Recognition (HTR) systems.

Perspective distortion (PD) leads to substantial alterations in the shape, size, orientation, angles, and spatial relationships of visual elements in images. Accurately determining camera intrinsic and extrinsic parameters is challenging, making it hard to synthesize perspective distortion effectively. The current distortion correction methods involve removing distortion and learning vision tasks, thus making it a multi-step process, often compromising performance. Recent work leverages the Möbius transform for mitigating perspective distortions (MPD) to synthesize perspective distortions without estimating camera parameters. Möbius transform requires tuning multiple interdependent and interrelated parameters and involving complex arithmetic operations, leading to substantial computational complexity. To address these challenges, we propose Log Conformal Maps (LCM), a method leveraging the logarithmic function to approximate perspective distortions with fewer parameters and reduced computational complexity. We provide a detailed foundation complemented with experiments to demonstrate that LCM with fewer parameters approximates the MPD. We show that LCM integrates well with supervised and self-supervised representation learning, outperform standard models, and matches the state-of-the-art performance in mitigating perspective distortion over multiple benchmarks, namely Imagenet-PD, Imagenet-E, and Imagenet-X. Further LCM demonstrate seamless integration with person re-identification and improved the performance. Source code is made publicly available at https://github.com/meenakshi23/Log-Conformal-Maps. 

Perspective distortion (PD) causes unprecedented changes in shape, size, orientation, angles, and other spatial relationships of visual concepts in images. Precisely estimating camera intrinsic and extrinsic parameters is a challenging task that prevents synthesizing perspective distortion. Non-availability of dedicated training data poses a critical barrier to developing robust computer vision methods. Additionally, distortion correction methods make other computer vision tasks a multi-step approach and lack performance. In this work, we propose mitigating perspective distortion (MPD) by employing a fine-grained parameter control on a specific family of Möbius transform to model real-world distortion without estimating camera intrinsic and extrinsic parameters and without the need for actual distorted data. Also, we present a dedicated perspectively distorted benchmark dataset, ImageNet-PD, to benchmark the robustness of deep learning models against this new dataset. The proposed method outperforms existing benchmarks, ImageNet-E and ImageNet-X. Additionally, it significantly improves performance on ImageNet-PD while consistently performing on standard data distribution. Notably, our method shows improved performance on three PD-affected real-world applications—crowd counting, fisheye image recognition, and person re-identification—and one PD-affected challenging CV task: object detection. The source code, dataset, and models are available on the project webpage at https://prakashchhipa.github.io/projects/mpd.

This paper introduces a new OCR dataset for historical handwritten Ethiopic script, characterized by a unique syllabic writing system, low-resource availability, and complex orthographic diacritics. The dataset consists of roughly 80,000 annotated text-line images from 1700 pages of 18th to 20th century documents, including a training set with text-line images from the 19th to 20th century and two test sets. One is distributed similarly to the training set with nearly 6,000 text-line images, and the other contains only images from the 18th century manuscripts, with around 16,000 images. The former test set allows us to check baseline performance in the classical IID setting (Independently and Identically Distributed), while the latter addresses a more realistic setting in which the test set is drawn from a different distribution than the training set (Out-Of-Distribution or OOD). Multiple annotators labeled all text-line images for the HHD-Ethiopic dataset, and an expert supervisor double-checked them. We assessed human-level recognition performance and compared it with state-of-the-art (SOTA) OCR models using the Character Error Rate (CER) and Normalized Edit Distance (NED) metrics. Our results show that the model performed comparably to human-level recognition on the 18th century test set and outperformed humans on the IID test set. However, the unique challenges posed by the Ethiopic script, such as detecting complex diacritics, still present difficulties for the models. Our baseline evaluation and dataset will encourage further research on Ethiopic script recognition. The dataset and source code can be accessed at https://github.com/bdu-birhanu/HHD-Ethiopic.

Interoperability is a central problem in digitization and sos engineering, which concerns the capacity of systems to exchange information and cooperate. The task to dynamically establish interoperability between heterogeneous cps at run-time is a challenging problem. Different aspects of the interoperability problem have been studied in fields such as sos, neural translation, and agent-based systems, but there are no unifying solutions beyond domain-specific standardization efforts. The problem is complicated by the uncertain and variable relations between physical processes and human-centric symbols, which result from, e.g., latent physical degrees of freedom, maintenance, re-configurations, and software updates. Therefore, we surveyed the literature for concepts and methods needed to automatically establish sos with purposeful cps communication, focusing on machine learning and connecting approaches that are not integrated in the present literature. Here, we summarize recent developments relevant to the dynamic interoperability problem, such as representation learning for ontology alignment and inference on heterogeneous linked data; neural networks for transcoding of text and code; concept learning-based reasoning; and emergent communication. We find that there has been a recent interest in deep learning approaches to establishing communication under different assumptions about the environment, language, and nature of the communicating entities. Furthermore, we present examples of architectures and discuss open problems associated with ai-enabled solutions in relation to sos interoperability requirements. Although these developments open new avenues for research, there are still no examples that bridge the concepts necessary to establish dynamic interoperability in complex sos, and realistic testbeds are needed.

This work examines the adaptability of Deep Perceptual Similarity (DPS) metrics to context beyond those that align with average human perception and contexts in which the standard metrics have been shown to perform well. Prior works have shown that DPS metrics are good at estimating human perception of similarity, so-called perceptual similarity. However, it remains unknown whether such metrics can be adapted to other contexts. In this work, DPS metrics are evaluated for their adaptability to different contradictory similarity contexts. Such contexts are created by randomly ranking six image distortions. Metrics are adapted to consider distortions more or less disruptive to similarity depending on their place in the random rankings. This is done by training pretrained CNNs to measure similarity according to given contexts. The adapted metrics are also evaluated on a perceptual similarity dataset to evaluate whether adapting to a ranking affects their prior performance. The findings show that DPS metrics can be adapted with high performance. While the adapted metrics have difficulties with the same contexts as baselines, performance is improved in 99% of cases. Finally, it is shown that the adaption is not significantly detrimental to prior performance on perceptual similarity. The implementation of this work is available online.

We reflect on the experiences in organizing and implementing a high-quality Blended Intensive Programme (BIP) as a joint international event. A BIP is a short programme that combines physical mobility with a virtual part. The 6-day event, titled “DigiHealth-AI: Practice, Research, Ethics, and Regulation”, was organized in collaboration with partners from five European nations and support from the EU’s ERASMUS+ programme in November 2023. We introduced a new learning method called ProCoT, involving large language models (LLMs), for preventing cheating by students in writing. We designed an online survey of key questions, which was conducted at the beginning and the end of the BIP. The highlights of the survey are as follows: By the end of the BIP, 84% of the respondents agreed that the intended learning outcomes (ILOs) were fulfilled, 100% strongly agreed that artificial intelligence (AI) benefits the healthcare sector, 62% disagree that they are concerned about AI potentially eliminating jobs in the healthcare sector (compared to 57% initially), 60% were concerned about their privacy when using AI, and 56% could identify, at least, two known sources of bias in AI systems (compared to only 43% prior to the BIP). A total of 541 votes were cast by 40 students, who were the respondents. The minimum and maximum numbers of students who answered any particular survey question at a given period are 25 and 40, respectively.

This six-volume set LNCS 14804-14809 constitutes the proceedings of the 18th International Conference on Document Analysis and Recognition, ICDAR 2024, held in Athens, Greece, during August 30–September 4, 2024.The total of 144 full papers presented in these proceedings were carefully selected from 263 submissions.The papers reflect topics such as: Document image processing; physical and logical layout analysis; text and symbol recognition; handwriting recognition; document analysis systems; document classification; indexing and retrieval of documents; document synthesis; extracting document semantics; NLP for document understanding; office automation; graphics recognition; human document interaction; document representation modeling and much more.

This six-volume set LNCS 14804-14809 constitutes the proceedings of the 18th International Conference on Document Analysis and Recognition, ICDAR 2024, held in Athens, Greece, during August 30–September 4, 2024.The total of 144 full papers presented in these proceedings were carefully selected from 263 submissions.The papers reflect topics such as: Document image processing; physical and logical layout analysis; text and symbol recognition; handwriting recognition; document analysis systems; document classification; indexing and retrieval of documents; document synthesis; extracting document semantics; NLP for document understanding; office automation; graphics recognition; human document interaction; document representation modeling and much more.