Affect Identification Accuracy Research Articles

Offline writer identification approach using moment features and high-order correlation functions

For text-independent writer identification(WI) tasks, this paper proposes a novel method based on semantic codebooks and two effective feature descriptors. This method requires constructing semantic codebooks consisting of various subimages and their labels. Moment features and high-order correlation functions are used to describe handwriting style, and the standard Euclidean distance function is used for distance measurement. Then, two-way analysis of variance(TW-ANOVA) is used to filter out character factors that affect identification accuracy. Finally, a combined measure obtained from multiple classifiers based on a fuzzy integral rule is used to determine the candidate writers. To verify the effectiveness of the system, experiments are performed using the Firemaker, IAM, CRUG-CN and Uyghur2016 databases. The evaluation results demonstrate better performance than most existing methods.

Image-based identification of optical quality and functional properties in inkjet-printed electronics using machine learning

AbstractWe propose a novel image-analysis based machine-learning approach to the fully-automated identification of the optical quality, of functional properties, and of manufacturing parameters in the field of 2D inkjet-printed test structures of conductive traces. To this end, a customizable modular concept to simultaneously identify or predict dissimilar properties of printed functional structures based on images is described and examined. An application domain of the concept in the printing production process is outlined. To examine performance, we develop a dataset of over 5000 test structures containing images and physical characteristics, which are manufactured using commercially available materials. Functional test structures are fabricated via a single-nozzle vector-based inkjet-printing system and thermally sintered. Physical characterization of electrical conductance, image capturing, and evaluation of the optical quality of the test structures is done by an automatic in-house built measurement station. Conceptionally, the design of a convolutional neural network is described to identify the optical quality and physical characteristics based only on acquired images. A mathematical apparatus that allows assessment of the identification accuracy is developed and described. The impact of printing resolution, of emerging defects in the geometry of printed structures, and of image quality and color space on the identification accuracy is analyzed. Quality groups related to the printing resolution that affect identification accuracy are determined. Supplementarily, we introduce not yet reported classification of processes related to the fabrication of printed functional structures, adopted from the process analytical technology.

Parentage‐based tagging using mothers balances accuracy and cost for discriminating between natural and stocked recruitment for inland fisheries

AbstractHatchery programmes are frequently used to supplement inland fisheries, yet achieving successful management outcomes often requires information on stocked versus naturally reproduced fish abundance. Parentage‐based tagging – genetically assigning offspring to their parents – has potential to be an effective approach for distinguishing stocked and naturally reproduced fish. However, several challenges may limit its application to inland fisheries, including genetic relatedness among populations that can affect identification accuracy and high costs of genotyping large broodstocks. Here, we demonstrate the efficacy of parentage‐based tagging based on broodmothers in the Lake Ontario Chinook Salmon fishery, which uses thousands of broodparents and has potential for substantial relatedness between stocked and naturally reproduced fish. Restricting parent sampling to broodmothers reduced costs by two‐thirds, was logistically pragmatic, and achieved >95% accuracy in distinguishing stocked from naturally reproduced salmon. Combined, these results highlight the potential wide applicability of parentage‐based tagging for assessing stocking programmes in inland waters.

Spread the Word: Enhancing Replicability of Speech Research Through Stimulus Sharing.

The ongoing replication crisis within and beyond psychology has revealed the numerous ways in which flexibility in the research process can affect study outcomes. In speech research, examples of these "researcher degrees of freedom" include the particular syllables, words, or sentences presented; the talkers who produce the stimuli and the instructions given to them; the population tested; whether and how stimuli are matched on amplitude; the type of masking noise used and its presentation level; and many others. In this research note, we argue that even seemingly minor methodological choices have the potential to affect study outcomes. To that end, we present a reanalysis of six existing data sets on spoken word identification in noise to assess how differences in talkers, stimulus processing, masking type, and listeners affect identification accuracy. Our reanalysis revealed relatively low correlations among word identification rates across studies. The data suggest that some of the seemingly innocuous methodological details that differ across studies-details that cannot possibly be reported in text given the idiosyncrasies inherent to speech-introduce unknown variability that may affect replicability of our findings. We therefore argue that publicly sharing stimuli is a crucial step toward improved replicability in speech research. https://doi.org/10.23641/asha.21985907.

Computer-aided superimposition via reconstructing and matching 3D faces to 3D skulls for forensic craniofacial identifications

Identification of human remains via craniofacial superimposition (CS) is one of the prominent research areas in the forensic sciences. CS makes use of imaging techniques to identify an unknown skull by matching it with the available face photographs of missing individuals. Life-size enlargement of the face image and orientating the skull to correspond to the posture seen in the face photograph are the two main problems that affect identification accuracy with both the conventional and the computer-aided methods. Unlike the existing techniques, this research proposes a 3D skull–3D face model superimposition (3D–3D) approach to address the above two issues. The proposed method commences by reconstructing the 3D face model from a given 2D face image using the mean simplified generic elastic model, followed by registering the face model to a 3D skull along the jaw line using the analytical curvature B-spline (AC B-spline). The accuracy index of the registration is then evaluated to suggest the degree to which the face image corresponds to a skull. The superimpositions of positive and negative cases were conducted on a set of 3D skulls versus a set of 2D face images. The accuracy indices of the registration results suggest that the AC B-spline is more robust in 3D–3D superimposition compared to the other existing methods. The full experimental results have demonstrated the potential of the proposed method as an assistive tool to the forensic scientists for craniofacial identifications.

The impact of concurrent linguistic tasks on participants’ identification of spearcons

Spearcons (time-compressed speech) may be a viable auditory display for patient monitoring; however, the impact of concurrent linguistic tasks remains unexamined. We tested whether different concurrent linguistic tasks worsen participants' identification of spearcons. Experiment 1 tested non-clinician participants' identification of multiple-patient spearcons representing 2 vital signs of 5 patients while participants performed no concurrent task, reading, or saying linguistic tasks. Experiment 2 tested non-clinician participants' identification of 48 single-patient spearcons while they performed no concurrent task, reading, listening, and saying linguistic tasks. In Experiment 1 the saying task worsened participants' identification of spearcons compared with no concurrent task or reading. In Experiment 2, the saying and listening tasks reduced participants' accuracy at identifying spearcons, but the reading task did not. Listening affected identification accuracy no differently than the saying task did. Concurrent auditory linguistic tasks worsen participants’ identification of spearcons, probably due to auditory modality interference in verbal working memory.

Missing Children Photograph Appeals: Does the Number of Appeals Affect Identification Accuracy Following a Short Recall Delay?

The study objectives were (1) to determine if there were any associations between the time spent observing fictional appeals and identification accuracy, (2) to establish if the number of missing children photographs observed influences identification accuracy and (3) to determine whether the number of missing children appeals observed influences identification accuracy following a short 3-day delay. A two-stage approach was utilised. Two hundred and forty-two participants observed one, four or eight mock missing children photographs followed by a short word memory distraction task and a target present line-up identification task. The second stage comprised of another target present line-up identification task presented after a short 3-day delay. One-way between-group ANOVAs indicate that observing one missing child photograph has significantly greater overall identification accuracy and lower identification error than viewing four or eight photographs immediately after observing the appeal and following a 3-day delay. Additional analyses found that the identification accuracy was significantly higher immediately after observation compared with the identification accuracy following a 3-day delay. The findings demonstrate the necessity for improving missing children appeals. Due to the exploratory nature of the study, additional research is required to explore these factors further.

Polish listeners’ perception of vowel inherent spectral change in L2 English

Abstract This paper describes a perception experiment with Polish listeners involving vowel inherent spectral change (VISC) in L2 English. A forced-choice rhyming task employing the Silent Center (SC) paradigm revealed relatively uniform effects of stimulus type (SC, Initial, Middle, Final) on accuracy across two proficiency groups, despite greater overall accuracy on the part of the more proficient users. Analysis of individual vowel pairs used in the rhyming trials revealed some effects of proficiency on the degree to which formant movement in the stimuli affected identification accuracy. This research contributes to the relatively sparse literature on VISC in L2 acquisition. Phonological considerations underlying the degree of VISC in Polish and English are also discussed.

Image-Matching Based Identification of Store Signage Using Web-Crawled Information

We address automatic matching of street images with relevant web resources to enable the identification of store signage in street images. Identification methods for signage usually involve image matching, which attempts to match query images to other similar viewings using pre-labeled copies from a target data set. Manual target data set, such as a fingerprinting database can ensure high-quality data but collected data must be fed manually, which significantly adds costs. Utilizing web-crawled information is a way for automatic data set generation at lower cost, however, imbalanced and noisy data can adversely affect identification accuracy. Our work aims to resolve these issues. We propose a signage identifier in Web-crawled information – SIWI. The SIWI includes a web image data set construction method, which can self-generate high-quality data sets through automated web-mining, including data filtering and pruning strategies, which effectively reduce the identification error caused by noise, imbalance, and insufficient data. Furthermore, by applying a Hybrid Image Matching method that combines the deep learning approach with the feature point matching to signage identification without Optical Character Recognition, it can handle arbitrary signage designs. Because there is no specialized training involved, the same process should also work for any other locations without manual adjustment. An experimental result achieves 91% accuracy in a real-life application, which confirms its effectiveness.

Using Earcons to Monitor Multiple Patients

Clinicians often monitor the status of multiple patients who are out of the clinician’s field of view. An auditory display that intermittently conveys the vital signs of these patients through an earpiece may help clinicians detect problems with one or more patients. The auditory display could convey the status of multiple patients by representing a sequence of patients as a sequence of earcons. Earcons convey information through short, abstract tones that are played intermittently (Brewster, Wright, & Edwards, 1992). In recent work, Janata and Edwards (2013) created a set of 500 ms earcons that conveyed the oxygen saturation (SpO2) and heart rate (HR) levels of individual neonates. Their earcons used variations in tremolo (the amount of corrugation of the sound) to represent HR and variations in timbre (the amount of brightness of the sound) to represent SpO2. Their set of 25 earcons conveyed 5 levels of HR and SpO2; ‘Very High’, ‘High’, ‘Normal’, ‘Low’ and ‘Very Low’ for each variable. The earcons proved moderately successful for conveying the status of individual patients. We applied Janata and Edwards’ (2013) earcons to multiple-patient monitoring by placing the earcons in a sequence, each earcon representing the status of one patient. The intention was that the sequence of earcons would be played at regular intervals, such as every one to two minutes, to reassure the clinician that all is well or to alert them to early signs of deterioration in one or more patients. We refer to this as a cycling earcon display. The sequence begins with a reference tone, alerting and reminding the listener of the earcon sound associated with normal HR and SpO2 values. The reference tone is followed by a sequence of earcons separated by intervals of less than 1 s (one earcon for each patient). In our study we used only the ‘Very High’, ‘Normal’, and ‘Very Low’ earcons from the Janata and Edwards set to maximize the discriminability of the earcons. Two experiments were conducted with non-clinical participants to test the feasibility of the cycling earcon display for multiple-patient monitoring. We anticipated that accuracy in both experiments would be limited by auditory working memory (Baddeley, 2012). In Experiment 1, participants monitored 1, 5 or 9 simulated patients in a sequence amongst which there were either 1, 2 or 3 patients with abnormal values of HR and SpO2. Participants were asked to report the HR and SpO2 levels for the patients with abnormal values. The inter-stimulus interval (ISI) between earcons was 150 ms. Results showed that the number of patients in the sequence did not affect identification accuracy, but identification accuracy decreased as the number of patients with abnormal values increased from 1 ( Mdn = 97%) to 3 ( Mdn = 67%), p < .001. Accuracy may have been lower in conditions with more than one abnormal patient, because an ISI of 150 ms may not have allowed participants enough time to encode the sounds in working memory. In Experiment 2 we increased the ISI to see if accuracy could be improved. The number of patients in a sequence was fixed to 5 and the ISI was either 150 or 800 ms. Again, identification accuracy decreased as the number of abnormal patients increased from 1 to 3, p < .001, but accuracy was significantly better with an ISI of 800 ms ( Mdn = 89%) compared to an ISI of 150 ms ( Mdn = 83%), p < .001. Accordingly, having more time to encode the sounds may have helped participants to retain the information. Results from the two experiments suggest that with further testing and design, multiple patients could be monitored through a cycling earcon display. Although clinical monitoring loads of 3 abnormal patients amongst 9 patients are rare, our aim was to test the boundaries of participants’ ability to monitor this type of cycling earcon display. In future work, we will test improved cycling displays with clinician participants experiencing clinically relevant situations.

Single-word intelligibility testing in aphasia: Alternate forms reliability, phonetic complexity and word frequency

Background: We recently constructed a single-word speech intelligibility test intended to quantify magnitude of speech sound impairment in individuals with aphasia. To minimise listener learning and strategising, the test included a large set of possible (alternate) test forms and was constructed with high and diverse phonologic similarity among candidate words. Although the corpus was limited in phonetic complexity to single syllables, and although criteria for minimal word frequency were applied, it is possible that more fine-grained differences in phonetic complexity and/or word frequency may introduce varying levels of difficulty across alternate test forms and that reliability, therefore, may be compromised.Aims: The dual purposes of this study were to evaluate alternate forms reliability for the new intelligibility test and to determine whether word frequency and/or phonetic complexity affected word identification scores.Methods & Procedures: All words in the 600-word test corpus were coded for overall phonetic complexity and for frequency of occurrence in spoken English. Fifty-one versions of the target 50-word test were generated from this corpus by following designated pseudo-random selection procedures. Speech samples were collected from 13 speakers with aphasia, who each repeated three or four of these 50-word sets. Ten normal-hearing listeners were asked to indicate the words they thought the speakers were trying to say. Per cent accuracy was computed for each speaker, test form and target word.Outcomes & Results: The intra-class correlation within speakers was 0.97, indicating that the scores across alternate forms were highly reproducible. Analyses at the word level showed that both phonetic complexity and word frequency affected identification accuracy. The effects were seen in almost all participants whose intelligibility scores were in the impaired range.Conclusions: High frequency of occurrence and low phonetic complexity increase repetition accuracy for individuals with moderate to severe sound production difficulties and aphasia. However, the pseudo-random word selection in the examined word intelligibility test was sufficient to ensure strong alternate forms reliability. Further constraints on the word selection process for this test are not warranted.

The confidence-accuracy relationship for eyewitness identification decisions: Effects of exposure duration, retention interval, and divided attention.

Prior research points to a meaningful confidence-accuracy (CA) relationship for positive identification decisions. However, there are theoretical grounds for expecting that different aspects of the CA relationship (calibration, resolution, and over/underconfidence) might be undermined in some circumstances. This research investigated whether the CA relationship for eyewitness identification decisions is affected by three, forensically relevant variables: exposure duration, retention interval, and divided attention at encoding. In Study 1 (N = 986), a field experiment, we examined the effects of exposure duration (5 s vs. 90 s) and retention interval (immediate testing vs. a 1-week delay) on the CA relationship. In Study 2 (N = 502), we examined the effects of attention during encoding on the CA relationship by reanalyzing data from a laboratory experiment in which participants viewed a stimulus video under full or divided attention conditions and then attempted to identify two targets from separate lineups. Across both studies, all three manipulations affected identification accuracy. The central analyses concerned the CA relation for positive identification decisions. For the manipulations of exposure duration and retention interval, overconfidence was greater in the more difficult conditions (shorter exposure; delayed testing) than the easier conditions. Only the exposure duration manipulation influenced resolution (which was better for 5 s than 90 s), and only the retention interval manipulation affected calibration (which was better for immediate testing than delayed testing). In all experimental conditions, accuracy and diagnosticity increased with confidence, particularly at the upper end of the confidence scale. Implications for theory and forensic settings are discussed.

Impact of chronic hypercortisolemia on affective processing

Cushing syndrome (CS) is the classic condition of cortisol dysregulation, and cortisol dysregulation is the prototypic finding in Major Depressive Disorder (MDD). We hypothesized that subjects with active CS would show dysfunction in frontal and limbic structures relevant to affective networks, and also manifest poorer facial affect identification accuracy, a finding reported in MDD. Twenty-one patients with confirmed CS (20 ACTH-dependent and 1 ACTH-independent) were compared to 21 healthy control subjects. Identification of affective facial expressions (Facial Emotion Perception Test) was conducted in a 3 Tesla GE fMRI scanner using BOLD fMRI signal. The impact of disease (illness duration, current hormone elevation and degree of disruption of circadian rhythm), performance, and comorbid conditions secondary to hypercortisolemia were evaluated. CS patients made more errors in categorizing facial expressions and had less activation in left anterior superior temporal gyrus, a region important in emotion processing. CS patients showed higher activation in frontal, medial, and subcortical regions relative to controls. Two regions of elevated activation in CS, left middle frontal and lateral posterior/pulvinar areas, were positively correlated with accuracy in emotion identification in the CS group, reflecting compensatory recruitment. In addition, within the CS group, greater activation in left dorsal anterior cingulate was related to greater severity of hormone dysregulation. In conclusion, cortisol dysregulation in CS patients is associated with problems in accuracy of affective discrimination and altered activation of brain structures relevant to emotion perception, processing and regulation, similar to the performance decrements and brain regions shown to be dysfunctional in MDD.This article is part of a Special Issue entitled ‘Anxiety and Depression’.

When is an intervening line‐up most likely to affect eyewitness identification accuracy?

Purpose. Intervening line‐ups affect identification accuracy in subsequent line‐ups. We conducted 3 experiments to investigate the conditions under which viewing multiple line‐ups is more likely to affect eyewitness identification accuracy.Method. In each of the 3 experiments, a forensically relevant factor known to affect the accuracy of face recognition memory was manipulated to assess how the factor impacted the suggestive influence of an intervening line‐up on eyewitness identification accuracy in a subsequent test line‐up. These factors were (a) in Experiment 1, same‐race versus cross race target faces, (b) in Experiment 2, whether the intervening line‐up occurred on the day of the presentation phase (close to presentation) or 1 month later on the day of the subsequent test line‐up (far from presentation), and (c) in Experiment 3, whether the target face was presented for 10 seconds or 60 seconds.Results. In each experiment, factors associated with poorer memory for the target face led to a greater suggestive influence of the intervening line‐up on identification accuracy in the subsequent line‐up, evidenced by lower hit rates and higher false‐alarm rates.Conclusions. These findings suggest that the problem of decreased identification accuracy following the viewing of an intervening photograph is especially of concern when memory for the perpetrator is likely to be poor. Implications of these findings for interpreting line‐up results in the courtroom are discussed.

Role of Word-External Contexts in Native Speakers’ Identification of Vowel Length in Japanese

Five groups of native Japanese listeners were assigned to five conditions differing in word-external contexts. In the Intact condition, three types of target disyllables, /mVmV/, /mV:mV/, and /mVmV:/ were spoken in a carrier sentence at two speaking rates. In the other four conditions, the target disyllables of the Intact condition were excised from the original carrier sentence (Excised); embedded in the carrier sentence of the other rate (Mismatch); presented only with the preceding three syllables (Preceding), and presented only with the following three syllables (Following). The accuracy for identifying the word types was higher for the Intact than Excised and Mismatch conditions, indicating that the presence of the carrier sentence with an appropriate rate was important for accurate identification.It was also found that either the preceding or the following short phrase contained sufficient information for identifying the word types. Further, there were effects of the preceding and following phrases on both the first and second vowels of the targets, suggesting that the distant speech materials more than two phonemes away from a target in both sides can affect identification accuracy. Implications are discussed in terms of the adjacency principle for rate normalization.

Earwitnesses: effects of speech duration, retention interval and acoustic environment

AbstractAn experiment was conducted to investigate the reliability of voice lineups. More specifically, the experiment was designed to look into the effects of retention interval (an immediate test or after a week), speech duration (30 or 70 s) and acoustic environment (indoors or indoors and outdoors) on speaker identification accuracy. In addition, the relation between confidence assessments of both participants and test assistant on the one hand and identification accuracy was explored. A total of 361 participants heard the target voice in one of four exposure conditions (short or long text and speech samples recorded only indoors or indoors and outdoors). Half the participants were tested immediately after exposure to the target voice and half 1 week later. The results show that the target was correctly identified in 42% of cases. In the target‐absent condition there were 51% false alarms. Acoustic environment did not affect identification accuracy. There was an interaction between speech duration and retention interval in the target‐absent condition. When listeners were tested after a week, they made fewer false identifications if the speech sample was long. No effects were found when participants were tested immediately. Only the confidence scores of the test assistant had predictive value. Taking the confidence score of the test assistant into account therefore increases the diagnostic value of the identity parade. Copyright © 2004 John Wiley & Sons, Ltd.

Negligible effect of spatial precuing on identification of single digits.

The present study examined the effects of spatial preening on identification of a single object appearing in an otherwise empty visual field. A digit target was preceded by a valid, neutral, or invalid location cue, presented either peripherally or centrally. The target was followed by either a single mask or multiple masks covering the target and nontarget (empty) locations. Precuing significantly affected identification accuracy when multiple masks were used but had little effect when the target was followed by a single mask. The results strongly favor a model in which spatial precuing allows the contents of noncued locations to be excluded from decision (and possibly perception). Exclusion may or may hot facilitate performance, depending on what is there to be excluded. The role of spatial visual attention in modulating perception has intrigued psychologists for a long time. Helmholtz (1866/1924) noted that in a completely dark room, a person can concentrate his attention on any part of the room, so that when a spark of light illuminates the whole room, he will get an impression about the objects in that particular region only. Because the spark is too brief for an eye movement, Helmholtz reasoned that covert orienting of attention must be independent of the position and accommodation of the eyes. Modern experimental psychologists have adopted similar paradigms, albeit with better experimental controls, to study voluntary and involuntary deployment of spatial attention. In a typical experiment of this kind, a target appears in one of several locations. The manipulation of spatial attention is supposed to be accomplished by presenting a location cue shortly before the target display. This precue is valid when it indicates the location of the target. It is invalid when it cues a location where the target does not appear. It is neutral if it carries no information whatsoever about the location of the target. Researchers have examined effects of both peripheral cues (appearing near the location of the target) and

The effect of expectation on the identification of known and unknown persons

AbstractIn this experiment we investigated the influence of expectation, exposure time and jacket hood positioning on person identification. Thirty subjects, all employees of the TNO Institute for Perception, participated in the experiment. They were presented with slides showing known and unknown persons who were photographed under bad lighting conditions. Limited viewing conditions considerably deteriorated subjects' performance and under these circumstances all experimental manipulations significantly affected identification accuracy. Contrary to what was expected longer exposure times impaired performance. The results are discussed in light of recent research on face recognition (Bruce and Young, 1986; Read, Vokey, and Hammersley, 1990).

Juror decision making in eyewitness identification cases.

The lay-person's knowledge of the factors that influence eyewitness memory was examined by evaluating the manner in which mock jurors integrated eyewitness evidence to draw inferences about defendant culpability and the likelihood that an identification was correct. Three hundred and twenty-one undergraduates viewed a videotaped trial within which ten witness and identification factors were manipulated between trials. Manipulation checks showed that subjects demonstrated superior memory for the evidence and the manipulated variables had their intended impact on appropriate rating scales. However, only one variable, witness confidence, had reliable effects on subjects' perceptions of culpability, on the perceived likelihood that the identification was correct, and on several other relevant dependent variables. Eight variables that have been shown to affect identification accuracy in the empirical literature had trivial effects on mock jurors' inferences. It was concluded that lay-people are insensitive to the factors that influence eyewitness memory.

Natural-color and color-infrared photography for the identification of forest-stand density, height, and species composition

Natural-color and color-infrared aerial photography at scales of 1:30 000, 1:50 000, and 1:70 000 were evaluated for the interpretation of forest-stand density, height, and species class, for test areas in the boreal and foothills regions of Alberta. Accuracy was assessed by comparing photo interpreter identification to field measurements. When averaged over all scales, color film types did not differ in accuracy. Scale affected identification accuracy for density and species class. The 1:70 000 scale was most accurate for estimating density and least accurate for species class. Scale did not affect identification accuracy for 6-m height classes. Interpreter inventory experience and color-discrimination ability both affected accuracy for species class, but not density or height. Standard 1:15 000 scale black and white photography was not significantly more accurate than any of the other film–scale combinations for identification of density, height, or species class.