Research on detection techniques for pattern modifications of playing cards used in illegal gambling operations.

We investigated pattern-modified marked cards used in fraudulent gambling cases in Korea. These cards are printed with modifications to some of the repeated marks on the back, revealing the hand on the front and enabling fraudsters to deceive their victims. We proposed a method for identifying the modified part by first enhancing the card's color difference using an image processing technique and then calculating the similarity between the repeated basic patterns with a Siamese network. This method is fast and convenient, as it can determine the deformation with only 1 or 2 cards and can be implemented in mobile applications, allowing law enforcement officers to investigate quickly. The proposed method serves as a useful tool to aid document examiners in making judgments, as it does not require expensive equipment and effectively visualizes the alterations.

Identification of document paper using hybrid feature extraction.

Document forgery is a significant issue in Korea, with around ten thousand cases reported every year. Analyzing paper plays a crucial role in examining questionable documents such as marketable securities and contracts, which can aid in solving criminal cases of document forgery. Paper analysis can also provide essential insights in other types of criminal cases, serving as an important clue for solving cases such as the source of a blackmail letter. The papermaking process generates distinct forming fabric marks and formations, which are critical features for paper classification. These characteristics are observable under transmitted light and are created by the forming fabric pattern and the distribution of pulp fibers, respectively. In this study, we propose a novel approach for paper identification based on hybrid features. This method combines texture features extracted from images converted using the gray-level co-occurrence matrix (GLCM) approach and a convolutional neural network (CNN), with another set of features extracted by the CNN using the same images as input. We applied the proposed method to classification tasks for seven major paper brands available in the Korean market, achieving an accuracy of 97.66%. The results confirm the applicability of this method for visually inspecting paper products and demonstrate its potential for assisting in solving criminal cases involving document forgery.

Detection of hidden marks on Hwatu cards used in illegal gambling.

Hwatu is a popular card game widely played in both Korea and Japan. This study examined hwatu cards used in the fraudulent gambling in Korea. Fraudsters used the hwatu cards, with hidden marks printed on the back using special ink to identify the cards so that they could deceive unknowing game players. These marks are invisible to the naked eye under normal conditions and are only visible when wearing special lenses. When suspicious hwatu cards are sent to the forensic laboratory, detection of the hidden mark conducted by the microscope, video spectral comparator (VSC), and radiography, which are laborious. In this study, we developed visualization of the hidden mark on the hwatu cards by utilizing a set of the algorisms including color splitting, histogram normalization, FFT denoising, These algorithms were applied to mobile applications affording convenience and accessibility to help prevent fraud or to help law enforcement conduct an immediate investigation. The proposed method was confirmed to be simple and effective in detecting hidden marks on hwatu cards without the need for costly equipment.

Scanner model classification with characteristic brightness variations.

Analog documents and scanned digitized files are now considered equivalent in legal contexts, and the widespread supply of multi-functional printers has led to a surge in the use of scanned documents. With image editing tools, there has been more cases of forgery involving scanned files. This has highlighted the importance of integrity and authenticity verification of scanned documents submitted as court evidence. Extensive studies have been conducted on source scanner identification and detection of alteration in scanned documents. Past research usually relied on machine learning with Support Vector Machine (SVM) and Convolutional Neural Network (CNN), and was focused more on images rather than text documents. Brightness variations are produced depending on the repetitive arrangement and relative intensity of light sources, and such patterns can be clearly observed in scanned images by the Charged Coupled Device (CCD) type flatbed scanner. The separate image module of the Contact Image Sensor (CIS) also leads to characteristic brightness variations. To extract and enhance these brightness variations, image processing techniques such as separating color channel and adjusting gradation and contrast are applied. The proposed method was tested on five scanner models, and the results confirmed that each scanner had unique brightness variations. This study is the first to extract brightness variations as a unique characteristic of each scanner model and recognize the potential of brightness variations in source identification and manipulation detection. A major advantage is that brightness variations are physical, robust, and visible. The research will be expanded with multicolor documents, counterfeit documents, and text-independent detection.

A study on factors that affect error rates in handwriting examinations of Korean characters by forensic document examiners and non-experts.

Forensic handwriting examinations are often considered important in trials, and especially those related to property issues. There is also increasing demand by courts for the quantification of handwriting examination results. Notably, in forensic science, error rates in forensic handwriting examinations should be carefully quantified in order to ensure their reliability as evidence. The present study examined error rates in forensic handwriting examinations conducted by both forensic document examiners (FDEs) and non-experts. To this end, four FDEs affiliated with forensic science institutes and a group of 20 laypersons were asked to perform a forensic handwriting examination of Korean characters in various forms (long text, short text, and signature samples) in blind test settings; i.e., specific information about the test was not given. The test was composed of 180 questions. The results showed that the incorrect answers are much higher in the non-expert group than the expert group though; however, the percentage of "inconclusive opinion" answers was higher in the expert group. It was also found that, in the expert group, error rates could be lowered by allowing a joint examination (or a peer review) to be performed. Meanwhile, the expert group showed relatively high error rates when dealing with handwriting samples simulated or disguised, rather than those that contained a small number of characters, such as signature samples. In the non-expert group, financial reward did not contribute to increasing the correct answers (%) of handwriting examination but rather encouraged examiners not to choose "inconclusive opinion" answers. This result indicates that a financial reward may unintentionally affect the examination results. The major findings of the present study are of significance in that this study is the first attempt to specifically examine error rates in forensic handwriting examinations of Korean characters conducted by both expert and non-expert groups. This study also demonstrated that the exchange of opinions among FDEs affected the resultant error rates and overall examination results. It was also found that financial reward may affect handwriting examination results as well.

Classification algorithm using halftone features of counterfeit bills and CNN.

With recent advancements in image processing and printing technology, home printers have improved in performance and grown more widespread. As such, they have been increasingly used in counterfeiting and forgery. Most counterfeit bills in Korea have been created using home scanners and printers. The identification of printer model is thus necessary to rapidly track down criminals and solve crimes. Household printers can be largely divided into inkjet and laser printers. These two types of printers print halftone textures instead of continuous images. This study proposed a technique of printer classification based on halftone textures that can be observed in printed documents. Since halftone textures are expressed as periodic lattices, the images were transformed via FFT, which is highly effective at expressing periodicity. ResNet, known for its superior gradient flow, was used for training. The experiment was conducted on 12 color laser jets and 2 inkjets. Scans of bills printed by each printer were used, and halftone texture analysis was performed on these images for printer model classification. Each image was cropped into several parts; one of the cropped parts was analyzed. The analysis showed that laser printers could be 100% distinguished from inkjet printers. An accuracy of 98.44% was achieved in make classification. When 50 cropped images were used instead of a single image, the technique achieved 100% accuracy in model classification. The proposed technique is non-destructive; it offers high accessibility and efficiency as it can be performed using a scanner alone, without requiring additional optical equipment.

Use of atomic force microscopy in the forensic application of chronological order of toners and stamping inks in questioned documents.

This paper describes the application of the atomic force microscopy (AFM) as a nano-indentation method and introduces a new method of identifying the chronological order of the application of the toner and stamping ink on the surface of documents by removing either of them. Various toners were used as samples for the AFM nano-indentation method. The chronological order of the application of the toner and stamping ink with either the toner placed over the stamping ink or the stamping ink placed over the toner, could be identified, regardless of the kinds of toners made by various companies. This paper provides the new approach for physically removing the toner and checking the material below it to identify questioned documents, which allows the method to be used to appraise documents forensically. Blind testing has shown that the method to analyze the chronological order of toner-printed documents and the seal stamping on them could accurately identify the order in all samples, while minimizing damage to the samples.

Multiform Korean handwriting authentication by forensic document examiners.

Forensic document examiners of Multiform Korean handwriting were tested using blind trials. A small number of experts (4) were tested for their performance and the test involved three steps. The participants each conducted a one-person examination first, then paired up with another person to perform the two-person examination and then finally the four people came together to conduct a group examination. When the experts actively exchanged opinions, the percentage of misleading decisions decreased while the percentage of inconclusive opinions increased. The deviations in the percentages of misleading results for different handwriting samples (long, short, signature) were not significant, while the disguised handwriting results showed the highest percentage of misleading conclusions. A special attention to artificially modified handwriting is therefore warranted rather than focusing on the number of letters.

Invisible ink mark detection in the visible spectrum using absorption difference.

One of popular techniques in gambling fraud involves the use of invisible ink marks printed on the back surface of playing cards. Such covert patterns are transparent in the visible spectrum and therefore invisible to unaided human eyes. Invisible patterns can be made visible with ultraviolet (UV) illumination or a CCD camera installed with an infrared (IR) filter depending on the type of ink materials used. Cheating gamers often wear contact lenses or eyeglasses made of IR or UV filters to recognize the secret marks on the playing cards. This paper presents an image processing technique to reveal invisible ink patterns in the visible spectrum without the aid of special equipment such as UV lighting or IR filters. A printed invisible ink pattern leaves a thin coating on the surface with different refractive index for different wavelengths of light, which results in color dispersion or absorption difference. The proposed method finds the differences of color components caused by absorption difference to detect invisible ink patterns on the surface. Experiment results show that the proposed scheme is effective for both UV-active and IR-active invisible ink materials.

Flexibility of inorganic tennis ball structures inducing anion selectivity.

Inorganic tennis balls (ITBs), [[{Pt(betmp)(dach)}(2)Cu](2)(X)][X](3) (in which X=ClO(4) (-) (3), NO(3) (-) (4), Cl(-) (5) and Br(-) (6); dach=trans-1,2-diaminocyclohexane and betmp=bisethylthiomethylidenepropanedioate) and [[{Pt(dteym)(dach)}(2)Cu](2)(PF(6))][PF(6)](3) (7; dteym=1,3-dithiepane-2-ylidenemalonate), were prepared as crystals. Investigation of their X-ray crystal structures revealed that shapes of the cavities in ITBs show significant distortions that depend on the properties of the encapsulated anions. The CuCu* distance was observed to be longest in 7 and shortest in 5, the difference between them being 2.05 A. The flexibility of cavity structures of ITBs makes it possible to encapsulate various anions inside the cavity, while their distortions may be a reason for the difference in the encapsulating ability for anions, that is, anion selectivity. Especially, the distortions observed in 7 are so severe that the encapsulating ability of the cavity for PF(6) (-) is very low compared to other anions. The shapes of ITBs with ClO(4) (-) and BF(4) (-) ions inside their cavities are very similar; however, ClO(4) (-) is encapsulated by the cavity better than BF(4) (-), which is explicable by the difference of metal-anion interactions. This structural study on ITBs gives a clue to the origin of the anion selectivity of the cavity in ITBs previously investigated by (19)F NMR spectroscopy of the ITBs in methanol.

The non-templated empty cavity and its selective anion binding despite having similar shapes.

An inorganic tennis ball with an empty cavity was formed without any assistance of guest molecules, and found to bind various anions selectively depending on their size and copper-anion interaction strengths without much change of the shapes.

The First Inorganic "Tennis Ball" Encapsulating an Anion.

New balls please! Reaction of Cu(BF4 )2 with [(dach)PtII ] (dach=trans (±)-1,2-diaminocyclohexane) and bis(ethylthio)methylenepropanedioate (BETMP) gave [{(dach)Pt(BETMP)}2 Cu(BF4 )2 ] (1; shown schematically). Dimerization of 1 in methanol leads to the first inorganic "tennis ball" 2 [Eq. (1)]. A BF4- ion is encapsulated in the cavity of 2.