Freehand Sketches Research Articles

Aesthetic sensibility and technical skills of an architect as a result of the fine arts learning—Curricula changes at the Faculty of Architecture, Silesian University of Technology in Gliwice

The paper presents the consequences for the architectural profession resulting from the evolution of the process of fine arts teaching on the example of the changing curricula at the Faculty of Architecture, Silesian University of Technology. The curricula in arts subjects ranging from the 90s up till now will be analyzed. Conducted analysis of the changes lead to a number of conclusions about impoverishment of aesthetic sensitivity and artistic skills of students and contemporary graduates. Currently, students mostly use computer drawings because they have poor ability to create understandable freehand sketches. We postulate the return to the past, good practices, to increase the number of the fine arts teaching hours, seeking better links between engineering design and artistic as well. It is principle that the use of new technologies workshop (including a PC) must go hand in hand with advanced knowledge about art solutions in every architectural project.Keywords: Fine arts teaching programmes, handwritten sketches, architecture student’s aesthetic sensitivity.

A multi-layer deep fusion convolutional neural network for sketch based image retrieval

Abstract The purpose of this paper is to introduce a new approach for the free-hand sketch representation in the sketch based image retrieval (SBIR), where the sketches are treated as the queries to search for the natural photos in the natural image dataset. This task is known as an extremely challenging work for 3 main reasons: (i) sketches show a highly abstract visual appearance versus natural photos, fewer context can be extracted as descriptors using the existing methods, (ii) for the same object, different people provide widely different sketches, making sketch-photo matching harder, (iii) mapping the sketches and photos into a common domain is also a challenging task. In this paper, we address the cross-domain question using a strategy of mapping sketches and natural photos in multiple layers. For the first time, we introduce a multi-layer deep CNNs framework to train the multi-layer representation of free hand sketches and natural photos. We use Flickr15k dataset as benchmark for the retrieval and show that our learned representation significantly outperformances both hand-crafted features as well as deep features trained by sketches or photos.

Sketch-Based User Authentication With a Novel String Edit Distance Model

The vast majority of user authentication in digital applications is based on alphanumeric passwords. Yet, due to severe problems that might arise with this approach, various efforts have been made in the last decade to replace this authentication paradigm. One candidate for the prospective paradigm shift might be found in the field of graphical passwords. The present paper introduces a novel framework for user authentication based on freehand sketches. The basic idea is that during the registration phase a user draws an arbitrary sketch in a specific drawing canvas (rather than typing a password). Registered users can then be authenticated whenever they are able to reproduce their personal sketch with sufficient precision. The major challenge of such a system is twofold. First, it has to provide a certain degree of error-tolerance such that the authentication of genuine users can be smoothly accomplished. Second, the system should detect even subtle forgeries and reject possible intruders. The main contributions of this paper are as follows. First, we formally represent the underlying sketches by means of strings and present a general authentication algorithm that is based on structural pattern recognition. Second, we present a novel cost model that is particularly useful in conjunction with string matching. Third, by means of an exhaustive empirical investigation using both random and skilled forgeries (stemming from several hundreds of users) we empirically confirm the feasibility of this particular authentication framework in a real-world scenario.

Enhancing Freehand Sketching in Industrial Design: Description and Implementation of a Drawing Methodology for More Effective Representations

Enhancing Freehand Sketching in Industrial Design: Description and Implementation of a Drawing Methodology for More Effective Representations

Improving students’ freehand sketching skills in mechanical engineering curriculum

Freehand sketching is a fundamental skill in mechanical engineering and many other engineering disciplines. It not only serves as a communication tool among engineers, but plays a critical role in engineering design and problem solving. However, as computer-aided drafting has replaced traditional drawing classes nowadays, the training of students’ freehand sketching skills has been almost completely eliminated in modern engineering curricula. This paper describes the attributes of freehand sketching and its roles in several essential aspects of engineering; in particular, in its roles in problem solving, of which current literature has ignored. Representative examples are provided to show students’ freehand sketching skills in problem solving in a foundational undergraduate mechanical engineering course. Pedagogical suggestions are made on how to teach freehand sketching to engineering students.

Real-time shape recognition scheme on projected capacitive touchscreens

Most modern mobile devices are equipped with touchscreens as the main input hardware. Users can write text or draw shapes on the touchscreen to interact with apps. Therefore, accurate recognition of users’ freehand sketches becomes crucial for a device to receive correct instructions from users. This paper proposes a real-time scheme to recognize shapes drawn on the touchscreen. The proposed shape recognition scheme includes preprocessing, feature extraction and shape classification stages. Freehand strokes drawn by users are usually distorted and inaccurate. In preprocessing, this study uses the sampling technique to remove drawing imperfections such as small jagged noise or distorted strokes. In the feature extraction, we use a state machine to extract the length and curvature as the intrinsic features of a shape. In the final shape classification stage, a template-based approach is used to classify the input shape. A fitness score of the input shape to a template is calculated and the template with the highest score is chosen as the most matched shape. Experiment results show that the proposed real-time shape recognition has high accuracy and good performance.

Synergistic Instance-Level Subspace Alignment for Fine-Grained Sketch-Based Image Retrieval

We study the problem of fine-grained sketch-based image retrieval. By performing instance-level (rather than category-level) retrieval, it embodies a timely and practical application, particularly with the ubiquitous availability of touchscreens. Three factors contribute to the challenging nature of the problem: 1) free-hand sketches are inherently abstract and iconic, making visual comparisons with photos difficult; 2) sketches and photos are in two different visual domains, i.e., black and white lines versus color pixels; and 3) fine-grained distinctions are especially challenging when executed across domain and abstraction-level. To address these challenges, we propose to bridge the image-sketch gap both at the high level via parts and attributes, as well as at the low level via introducing a new domain alignment method. More specifically, first, we contribute a data set with 304 photos and 912 sketches, where each sketch and image is annotated with its semantic parts and associated part-level attributes. With the help of this data set, second, we investigate how strongly supervised deformable part-based models can be learned that subsequently enable automatic detection of part-level attributes, and provide pose-aligned sketch-image comparisons. To reduce the sketch-image gap when comparing low-level features, third, we also propose a novel method for instance-level domain-alignment that exploits both subspace and instance-level cues to better align the domains. Finally, fourth, these are combined in a matching framework integrating aligned low-level features, mid-level geometric structure, and high-level semantic attributes. Extensive experiments conducted on our new data set demonstrate effectiveness of the proposed method.

ADAPTIVE NEURAL NETWORK FOR SKETCH BASED IMAGE RETRIEVAL

In this paper, we present neural network approach for Sketch Based Image Retrieval (SBIR) using Histogram of Gradient (HOG) feature descriptor. This paper emphasis on back propagation Feed-forward Network (FFN) and Pattern Recognition Network (PRN) used for sketch based retrieval. Neural network is a popular tool used for pattern recognition and approximation of unknown nonlinear functions. We use features descriptor like Histogram of Gradient (HOG) for free hand and human face sketches and these features are used to training of network. Experimental results and analysis are based on CHUK and Flicker dataset, used for training and testing. Different similarity measure functions are discussed and used similarity between query by non-expert sketchers and database.

BASIC VISUAL DISCIPLINES IN HERITAGE CONSERVATION: OUTLINE OF SELECTED PERSPECTIVES IN TEACHING AND LEARNING

Abstract. Acknowledgement of the value of a basic freehand sketch by the information and communication community of researchers and developers brought about the advanced developments for the use of sketches as free input to complicated processes of computerized visualization, so as to make them more widely accessible. However, a sharp reduction and even exclusion of this and other basic visual disciplines from education in sciences, technology, engineering and architecture dramatically reduces the number of future users of such applications. The unique needs of conservation of cultural heritage pose specific challenges as well as encourage the formulation of innovative development tasks in related areas of information and communication technologies (ICT). This paper claims that the introduction of basic visual disciplines to both communities is essential to the effectiveness of integration of heritage conservation needs and the advanced ICT development of conservation value, and beyond. It provides an insight into the challenges and advantages of introducing these subjects in a relevant educational context, presents some examples of their teaching and learning in the modern environment, including e-learning, and sketches perspectives to their application.

Evaluation of a traceability approach for informal freehand sketches

Most engineers and designers prefer to use large drawing boards such as whiteboards or flip charts for the initial collaborative sketching of a system’s models. Large interactive displays have recently begun to replace these physical drawing boards, blurring the line between freehand sketching and toolkit-aided modeling. While digital boards offer more flexibility in drawing and navigating models, they must also provide appropriate cognitive support for frequent shifts of focus and navigation between related artifacts. Furthermore, automated assistance in uncovering potential inconsistencies and contradictions between model sketches would be beneficial so that users do not get lost amid their sketches. In this paper, we discuss an approach to create relationships between the elements of informal hand-drawn sketches on large interactive displays by combining fuzzy search with classic information retrieval techniques. The identification and maintenance of relationships is particularly challenging because we are working with hand-drawn and hand-lettered model sketches rather than the syntactically clean models created with digital modeling toolkits. We evaluated our approach by analyzing 89 model sketches from 16 industry projects and found that it identifies relations between sketched model elements with high precision and recall.

Design of tasks for online assessment that supports understanding of students’ conceptions

In the present study, we ask whether and how online assessment can inform teaching about students’ understanding of advanced concepts. Our main goal is to illustrate how we study design of tasks that support reliable online formative assessment by automatically analyzing the objects and relations that characterize the students’ submissions. We aim to develop design principles for e-tasks that have the potential to support the creation of rich and varied response spaces that reflect convincingly the students’ perceptions. We focus on studying the design principles of such an interactive rich task, and the representations and tools that support automatic real-time analysis of submitted answers, primarily in the form of free-hand sketches. Using a design research methodology, we describe a two-cycle study focusing on one e-task concerning tangency to the graph of a function. We characterize the mathematical attributes of examples constructed by students in an interactive environment. Checking the correctness of answers is only one of the functions of the STEP platform that we use. That platform can identify submissions that contain partial information (e.g., missing or misplaced tangency points), can categorize these answers, and allow the teacher to analyze them further. The reported analysis demonstrates how the design of the tasks and the characterization of mathematical attributes can help to expand our understanding of different ways of conceptualizing.

DeepSketch 3

Freehand sketches are a simple and powerful tool for communication. They are easily recognized across cultures and suitable for various applications. In this paper, we use deep convolutional neural networks (ConvNets), state-of-the-art in the field of sketch recognition, to address several applications of automatic sketch processing: complete and partial sketch recognition, sketch retrieval using query-by-example (QbE), and sketch-based image retrieval (SBIR) i.e the retrieval of images using a QbE paradigm but where the query is a sketch. We first focus on improving sketch recognition. For this purpose we compare different ConvNet architectures, training paradigms and data fusion schemes. This enabled us to outperform previous state-of-the-art in two large scale benchmarks for sketch classification. We achieved a mean average accuracy of 79.18% for the TU-Berlin sketch benchmark and 93.02% for the sketchy database. For partial sketch recognition, we were able to produce a system that achieves a mean average accuracy of 52.58% with only 40% of the strokes. We then conduct a comprehensive study of ConvNets features to enhance sketch retrieval and image retrieval, using a kNN similarity search paradigm in the ConvNet feature space. For the sketch retrieval tasks, we compare the performance obtained with features extracted from various depths (ConvNet layers) using one of the best performing model from the previous work. For the sketch-based image retrieval (SBIR), a sketch query is used to retrieve images of objects that belong to the same category, or even with a shape and pose close to the sketch query. The main challenge in the field of SBIR is to obtain efficient cross-domain features for sketch-image similarity measure. For this, besides comparing features extracted from different depth, we additionally compare different training approaches (some novel) for the ConvNets applied to sketches and images. Eventually, our best SBIR system achieves state-of-the-art results on the sketchy database (close to 40% recall at k = 1).

Rethinking the graphic trace in performative drawing

ABSTRACTThis article critically investigates the ‘graphic trace’, commonly perceived in drawings as marks left from physical actions. It is a notion fundamental to current art practices engaging performance and experimental drawing. The graphic trace is investigated through ‘inscription’, which is popularly interpreted as the visual expression of thought through marks or imprints of physical movements, from free-hand sketching to tracing choreographic movements. A critique of this inscriptive ideology shows that the inscribed trace as ‘line’ expresses thought under vitalist schemas exemplified by Bergson’s notion of multiplicity, that life is prompted by a creative event, and Deleuze’s articulation of such an event as ‘lines of thought’. The critique proposed in this article is that a more radically discursive and exceptional event, or ‘multiplicity’, does not really take place. An overview is given of performative, choreographic and process-led practices since the 1970s, while unpacking philosophical concepts of gesture, movement and embodiment. The conclusion lays out the paradox that the graphic trace stultifies thinking, offsetting a more materialist kind of event that affirms discourse in exceptionally different ways.

Object Category Understanding via Eye Fixations on Freehand Sketches.

The study of eye gaze fixations on photographic images is an active research area. In contrast, the image sub-category of freehand sketches has not received as much attention for such studies. In this paper, we analyze the results of a free-viewing gaze fixation study conducted on 3904 freehand sketches distributed across 160 object categories. Our analysis shows that fixation sequences exhibit marked consistency within a sketch, across sketches of a category and even across suitably grouped sets of categories. This multi-level consistency is remarkable given the variability in depiction and extreme image content sparsity that characterizes hand-drawn object sketches. In this paper, we show that the multi-level consistency in the fixation data can be exploited to 1) predict a test sketch's category given only its fixation sequence and 2) build a computational model which predicts part-labels underlying fixations on objects. We hope that our findings motivate the community to deem sketch-like representations worthy of gaze-based studies vis-a-vis photographic images.

A social network supported CAI model for tacit knowledge acquisition

Freehand sketching is one of the most important and commonly used methods of generating and sharing budding ideas during the conceptual development portion of the preliminary phase of design. To develop one’s skills, prolonged practice, acquiring instant feedback and suggestions while practicing are invaluable. The two key and indispensable parts of learning draftsmanship are viewing and commenting on large numbers of free hand sketches. However, due to insufficient educational resources, instructors must spend most of their time engaged in class-room teaching, reducing the time allotted for one-on-one discussion and specialized assistance. Furthermore, the lack of sketch grading criteria can prevent students from developing proper insights into the essentials of sketching. As a result, students neither receive personalized feedback nor acquire adequate training in critiquing freehand sketching skills. These factors decrease learning effectiveness and negatively impact learning motivation. In order to solve this problem, this research has created a discussion platform on Facebook that utilizes the learning characteristics essential to developing proficiency in freehand sketching. It includes practice, observation, and comments. It has been found that this cultivates the subjects’ ability to judge freehand sketch quality and increases learning motivation and effectiveness through the process of peer-assessment. After participating in the one-semester teaching experiment, the abilities of the experimental group were significantly better than those of the control group, demonstrating that the online sketch discussion platform has a significant impact on freehand sketch learning.

FEAsy: A Sketch-Based Tool for Finite Element Analysis

Freehand sketching is an integral part of early design process. Recent years have seen an increased interest in supporting sketching in computer-based design systems. In this paper, we present finite element analysis made easy (FEAsy), a naturalistic environment for static finite element analysis. This tool allows users to transform, simulate, and analyze their finite element models quickly and easily through freehand sketching. A major challenge here is to beautify freehand sketches, and to this extent, we present a domain-independent, multistroke, multiprimitive method which automatically detects and uses the spatial relationships implied in the sketches for beautification. Further, we have also developed a domain-specific rules-based algorithm for recognizing commonly used symbols in finite element analysis (FEA) and a method for identifying different contexts in finite element modeling through combined interpretation of text and geometry. The results of the user study suggest that our proposed algorithms are efficient and robust. Pilot users found the interface to be effective and easy to use.

The Emergence of Edge Computing

Industry investment and research interest in edge computing, in which computing and storage nodes are placed at the Internet's edge in close proximity to mobile devices or sensors, have grown dramatically in recent years. This emerging technology promises to deliver highly responsive cloud services for mobile computing, scalability and privacy-policy enforcement for the Internet of Things, and the ability to mask transient cloud outages. The web extra at www.youtube.com/playlist?list=PLmrZVvFtthdP3fwHPy_4d61oDvQY_RBgS includes a five-video playlist demonstrating proof-of-concept implementations for three tasks: assembling 2D Lego models, freehand sketching, and playing Ping-Pong.

Features from a Single Vector Pressure Stroke

Freehand sketching in a real-time 3D styling system presents a different way to create a 3D model from the traditional CAD system. Strokes are the most common and useful objects in the expression of a stylist’s intention by using the gesture commands and in the construction of geometries. Not only are they sketched freely as drawing on a paper with a pen, but also they can be converted automatically into spline curves and then can be used to form a surface. Therefore, it is necessary to investigate the features of stroke, the extraction and identification of these features, and the applications. Here, the features from a single vector pressure stroke have been discussed in detail according to their applications in an automotive freehand styling system in the early stage of conceptual design. The features have been divided into three parts: the input features, the calculable feature, and the added features. Over a hundred features have been defined and classified with the geometry or performance attributes. The features proposed have been applied in the identification of gesture commands, the expression of art vector stroke by pseudoantialiasing method, and a novel method to generate a spatial curve directly by the pressure of stroke in AutoSketch system.

Conceptual design of jewellery: a space-based aesthetics approach

Conceptual design is a field that offers various aesthetic approaches to generation of nature-based product design concepts. Essentially, Conceptual Product Design (CPD) uses similarities based on the geometrical forms and functionalities. Furthermore, the CAD-based freehand sketch is a primary conceptual tool in the early stages of the design process. The proposed Conceptual Product Design concept is dealing with jewelleries that are inspired from space. Specifically, a number of galaxy features, such as galaxy shapes, wormholes and graphical representation of planet magnetic field are used as inspirations. Those space-based design ideas at a conceptual level can lead to further opportunities for research and economic success of the jewellery industry. A number of illustrative case studies are presented and new opportunities can be derived for economic success.

Establishment of Reference Coordinates for Free-hand Sketching

Establishment of Reference Coordinates for Free-hand Sketching