Improving the Performance of Frequently Used Korean Handwritten Character Verification Based on Artificial Intelligence through Multimodal Fusion

Handwriting verification is a biometric recognition field that identifies individuals’ unique characteristics contained in their handwriting. A single written character shows subtle differences depending on habits accumulated over time or the manner of writing. Based on this, it is often adopted in forensic investigations and as evidence in court. Existing handwriting verification is conducted by an expert, and is affected by the expert’s ability or subjectivity, causing different results to arise depending on the expert. Therefore, we propose a handwriting verification method that excludes human subjectivity and has objectivity. Using computer vision and artificial intelligence (AI), we derived results that excluded human subjectivity, and the judgment strength was expressed through a likelihood ratio. To improve the existing method’s accuracy, we performed a more accurate verification through multimodal use from the biometric field. Multimodal handwriting verification is conducted using up to four characters (not just one) because individual handwriting in each character is different. For learning, n-fold tests were conducted to maintain test objectivity, and the average performance of single character-based verification was 80.14% and the multimodal method averaged 88.96%. Here, we proposed the objectivity of handwriting verification through learning using AI, and show that performance improved through multimodal fusion.

Japanese orthographic complexity and speech duration in a reading task

The number of letters in a word’s orthographic form can affect speech duration (Brewer, Jordan B. 2008. Phonetic reflexes of orthographic characteristics in lexical representation. University of Arizona Doctoral Dissertation; Warner, Natasha, Allard Jongman, Joan Sereno & Rachèl Kemps. 2004. Incomplete neutralization and other sub-phonemic durational differences in production and perception: Evidence from Dutch. Journal of Phonetics 32(2). 251–276. Previous research in this area has been limited to studies of languages with alphabets. The current study expands upon this previous research by investigating effects on speech duration from units of orthographic complexity potentially analogous to letter length in Japanese, a language with a logography. In a modified version of Brewer, Jordan B. 2008. Phonetic reflexes of orthographic characteristics in lexical representation. University of Arizona Doctoral Dissertation, reading task, native Japanese-speaking participants were audio-recorded reading pairs of homophonous words that varied by: 1) number of pen strokes in a single character; or 2) number of whole characters in their orthographic forms. Two-character words were produced significantly longer than one-character words. No significant effect was found from pen strokes on speech duration. These results are presented as evidence that the orthographic duration effect observed in previous studies is not limited to languages with alphabetic writing systems.

Exploring the ‘Rolling Unmasking Effect’ of Downwind Odor Dispersion from Model Plant and Animal Sources

Solving environmental odor issues can be confounded by many analytical, technological, and socioeconomic factors. Considerable know-how and technologies can fail to properly identify odorants responsible for the downwind nuisance odor and mitigate it for the affected citizenry. We propose enabling solutions to environmental odor issues by utilizing troubleshooting techniques developed for the food, beverage, and consumer products industries. We showed that the downwind odorant impact-priority ranking process can be definable and relatively simple. The initial challenge is the prioritization of environmental odor character from the perspective of the impacted citizenry downwind. In this research, we aim at summarizing three natural models of the rolling unmasking effect (RUE) and discuss them more systematically in the context of the proposed downwind environmental odor prioritization approach. Regardless of the size and reach of an odor source, a simplification of odor character and composition typically develops with downwind dilution. The extreme odor simplification-upon-dilution was demonstrated for two plant varieties, prairie verbena and Virginia pepperweed. Their downwind odor frontal boundaries were dominated by single, character-defining odorants; p-cresol-dominated ‘barnyard’ odor, and benzyl mercaptan-dominated ‘burnt match’ odor, respectively. The P.T. porcupine downwind odor frontal boundary was dominated by two potent, character-defining odorants: (1) ‘onion’/‘body odor’ odorant #1 and (2) ‘onion’/‘grilled’ odorant #2. In contrast with their downwind boundary simplicities, each odor source presented considerable compositional complexity and composite character difference near the source. The proposed RUE approach’s ultimate significance is the illustration of naturally occurring phenomena that explain why some environmental odors and their sources can be challenging to identify and mitigate using the analytical only approach (focused on compound identities and concentrations). These approaches rarely move beyond comprehensive lists of compounds being emitted by the source.

TAMIZHİ: Historical Tamil-Brahmi Script Recognition Using CNN and MobileNet

Computational epigraphy is the study of an ancient script where the computer science and mathematical model is relatively built for epigraphy. The Tamil-Brahmi inscriptions are the most ancient of the extant written of the Tamil. The inscriptions furnish valuable information on many aspects of life in the ancient Tamil country from a period anterior to the literary age of Sangam. The recognition of the script and systematic analysis of the script is required. The recognition of this script is complex, containing various curves for a single character and the style of writing overlap with curves and lines. Generating corpus of the script is necessary, since it is the initial step for computational epigraphy. The archaeological department has supported the raw data that helped to develop a corpus of Tamizhi. In this article, we have implemented a convolution neural network in various ways, i.e., (i) Training the CNN model from scratch a Softmax classifier in a sequential model (ii) using MobileNet: Transfer learning paradigm from a pre-trained model on a Tamizhi dataset (iii) Building Model with CNN and SVM (iv) SVM for evaluation of best accuracy to recognize handwritten Brahmi characters. To train the CNN Model an extensive TAMIZHİ handwritten Brahmi Dataset of 1lakh and 90,000 isolated samples for the character has been created and deployed. The designed dataset consists of 9 vowels and 18 consonants and 209 class so researchers can use machine learning. MobileNet outperformed among all the models implemented with the accuracy of 68.3%, whereas other algorithm ranges from 58% to 67% with respect to the Tamizhi dataset. MobileNet model is trained and tested for the dataset of vowels (8 class), consonants (18 class), and consonants vowels (26 class) with the accuracy of 98.1%, 97.7%, 97.5%, respectively.

Robust Korean License Plate Recognition Based on Deep Neural Networks

With the rapid rise of private vehicles around the world, License Plate Recognition (LPR) plays a vital role in supporting the government to manage vehicles effectively. However, an introduction of new types of license plate (LP) or slight changes in the LP format can break previous LPR systems, as they fail to recognize the LP. Moreover, the LPR system is extremely sensitive to the conditions of the surrounding environment. Thus, this paper introduces a novel deep learning-based Korean LPR system that can effectively deal with existing challenges. The main contributions of this study include (1) a robust LPR system with the integration of three pre-processing techniques (defogging, low-light enhancement, and super-resolution) that can effectively recognize the LP under various conditions, (2) the establishment of two original Korean LPR approaches for different scenarios, including whole license plate recognition (W-LPR) and single-character license plate recognition (SC-LPR), and (3) the introduction of two Korean LPR datasets (synthetic data and real data) involving a new type of LP introduced by the Korean government. Through several experiments, the proposed LPR framework achieved the highest recognition accuracy of 98.94%.

Of Chimeras, Harmony, and Kintsugi: Towards a Historicist Epistemology of Paleontological Reconstruction, Theory-Change, and Exploring Heuristics

I analyze the epistemic strategies used by paleontologists between the early 19th and early 20th centuries to reconstruct features of ancient organisms from fossilized bodies and footprints by presenting two heuristics: (1) a “claim of harmony” which posits the harmonious interaction of natural objects in order for complex systems to be simplified and (2) the “kintsugi heuristic” which is used inter-theoretically to explore new claims of harmony. I apply these to three successive historical cases: Georges Cuvier’s laws of correlation, the panpsychist paleontology of Edward Drinker Cope, and the single-character approach of Henry Fairfield Osborn.

Application of grammar-based codes for lossless compression of digital mammograms

A newly developed grammar-based lossless source coding theory and its implementation was proposed in 1999 and 2000, respectively, by Yang and Kieffer. The code first transforms the original data sequence into an irreducible context-free grammar, which is then compressed using arithmetic coding. In the study of grammar-based coding for mammography applications, we encountered two issues: processing time and limited number of single-character grammar G variables. For the first issue, we discover a feature that can simplify the matching subsequence search in the irreducible grammar transform process. Using this discovery, an extended grammar code technique is proposed and the processing time of the grammar code can be significantly reduced. For the second issue, we propose to use double-character symbols to increase the number of grammar variables. Under the condition that all the G variables have the same probability of being used, our analysis shows that the double- and single-character approaches have the same compression rates. By using the methods proposed, we show that the grammar code can outperform three other schemes: Lempel-Ziv-Welch (LZW), arithmetic, and Huffman on compression ratio, and has similar error tolerance capabilities as LZW coding under similar circumstances.

Application of grammar-based codes for lossless compression of digital mammograms

A newly developed grammar-based lossless source coding theory and its implementation was proposed in 1999 and 2000, respectively, by Yang and Kieffer. The code first transforms the original data sequence into an irreducible context-free grammar, which is then compressed using arithmetic coding. In the study of grammar-based coding for mammography applications, we encountered two issues: processing time and limited number of single-character grammar G variables. For the first issue, we discover a feature that can simplify the matching subsequence search in the irreducible grammar transform process. Using this discovery, an extended grammar code technique is proposed and the processing time of the grammar code can be significantly reduced. For the second issue, we propose to use double-character symbols to increase the number of grammar variables. Under the condition that all the G variables have the same probability of being used, our analysis shows that the double- and single-character approaches have the same compression rates. By using the methods proposed, we show that the grammar code can outperform three other schemes: Lempel-Ziv-Welch (LZW), arithmetic, and Huffman on compression ratio, and has similar error tolerance capabilities as LZW coding under similar circumstances.

A History of Motives—Theory and Analysis

Chapter 3 provides a history of the role of motives in Western music theory and analysis. The first section covers 1600–1750 C.E., the last period in which motive remained in its conceptual prehistory. At that time, the preeminent musical structure was the “figure,” a passage of music that conveyed a single character. The second section covers 1750–1890, a period in which the influence of figures waned as authors began theorizing about the smaller musical cells that make melodies logical, pleasant, and memorable. The third section of the survey concentrates on the work of Arnold Schoenberg, the composer-theorist who did the most during that time to popularize motive-based views of music. The fourth section covers 1950 to 2010, a period marked by stark changes in how motive was conceived and handled in analysis. Specifically, motives in the late twentieth century underwent intense fragmentation, a “boiling away” of their elements, often leaving behind only pitch intervals and/or rhythms. The chapter closes with a rumination on past and present conventions of motive and motivic analysis, laying groundwork for the rules and conventions to follow in chapters 4–7, the methodology portion of Musical Motives.

Golding’s Narrowed Attempts at Defining Human Nature in Lord of the Flies

This paper is an attempt to prove the assumption that William Golding is a failure who claims to have written his novel Lord of the Flies on the idea of human nature. He considers that he wrote about human nature in general, but he is a Western and has those ideas of being superior to other people. He takes all his characters from among the English boys. Not a single character who is shown as civilized belongs to a marginalized race. This act of Golding reveals his ethnocentric attitude. He does not bother to include a female character in this novel. All his characters are male. It shows his androcentric nature. Though he tries to put the evil like every man whenever he wants to show the brutality or savagery of a human, in the form of his chosen English boys, he portrays them as the hunters of Africa or paints them with mud. In doing so, he is affiliating savagery with the blacks and Indians. Thus, he propagates the same stereotypical concept of “Orients” as uncivilized and savages. Golding relies solely on the biological factors of human nature. He ignores to consider any social problem for the conflict of the two groups of boys. These social factors may include political system, religion, or Marxism. This research work has proved that Golding’s self-critique of human nature in the novel is a failure on his part.